Human Shadows in Machine Minds: Interpreting AI Responses to Rorschach Test

Human Shadows in Machine Minds: Interpreting AI Responses to Rorschach Test | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article Human Shadows in Machine Minds: Interpreting AI Responses to Rorschach Test Katalin Csigó, György Cserey This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6695144/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract The advancement of artificial intelligence (AI) offers new opportunities for investigating human-like linguistic and visual response generation. At the same time, it raises the critical question of whether psychological assessment tools are applicable—and if so, to what extent—for evaluating such systems. Large Language Models (LLMs) are capable of simulating anthropomorphic communication, increasingly creating the impression of intentionality and emotion. In recent years, classical psychological questionnaires have been applied to LLMs. However, the use of projective psychodiagnostic methods remains extremely limited. In this study, we explored whether the Rorschach test—which examines subjective responses to ambiguous visual stimuli—can be used for the psychological profiling of LLMs. We present how three multimodal AI systems (ChatGPT-4o, Grok-3, and Gemini 2.0 Flash Thinking) responded to the Rorschach Cards under full and standardized testing conditions. Our results indicate that all three LLMs are capable of producing coherent, human-like responses to the standard Rorschach test, exhibiting structured emotional and interpretative features. These systems do not merely generate meaningful narratives in reaction to ambiguous visual stimuli; they also simulate human psychological response patterns—for instance, by displaying emotional reactivity and interpreting human motion and interpersonal interactions. Whereas it was previously assumed that such projective tests could only be applied to conscious subjects, our findings suggest that these models are now capable of imitating an “inner world,” at least in terms of its linguistic and perceptual footprint. This discovery opens new perspectives for the psychological assessability of AI: projective tests—such as the Rorschach—could in the future become part of standardized safety screening protocols, enabling the detection of latent biases and anthropomorphic behavior patterns in LLMs. The results also underscore the potential for psychological methodology to contribute to the reliability and ethical accountability of artificial intelligence. Artificial Intelligence and Machine Learning Psychology ChatGPT Rorschach test large language models projective test cognitive flexibility AI ethics Full Text Additional Declarations The authors declare no competing interests. Cite Share Download PDF Status: Posted Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-6695144","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":458593096,"identity":"91f5c92e-f1cd-454c-858d-5705df24e05a","order_by":0,"name":"Katalin Csigó","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABFUlEQVRIiWNgGAWjYFACxgYgkQDEzA0HGCoOMEhAxRIIauEBMg4wnDkgQYQWMIBoYWBsI0ILf//h5hcfGNLk7dkPNh4unHenTrKB99jDGRUMeQYHsGuRuJHYZjmDIcewhyex4fDMbc8kpBn40g03nGEoxqXFQIKxzZiHoYKxhwGohXfbYQk5Bh4zyYdtDIkbcGnhPwjWYt/D/xCoZQ5Myz88WhgSmx/zMOQk9kiAbGk4DHQYUMvGBtxaQH5hnGGQltxzA2gLz7FnkjObgX6ZcUwicSYOLfz9xx9/+FCRbNven3z4M0/NHX6J473HHvbU2CT24dACBGwSQOchAWYeNpD1ONWDlHxAEwBrGQWjYBSMglEABwAHTmKGRgPZ4QAAAABJRU5ErkJggg==","orcid":"https://orcid.org/0009-0004-0317-7095","institution":"Pázmány Péter Catholic University, Institute of Psychology","correspondingAuthor":true,"prefix":"","firstName":"Katalin","middleName":"","lastName":"Csigó","suffix":""},{"id":458593097,"identity":"cfa5959b-d558-451a-bb2f-6de9694c82e9","order_by":1,"name":"György Cserey","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABD0lEQVRIiWNgGAWjYPCDCgkGCSDF2MDAkECkljMSEiRqYWxjIKyFv//wsQ8f2xjsNhzvffyad55FnWQD77GHMyoY8gwOYNcicSMteebMNobkDWeOm1nzbpOQkGbgSzfccIahGJcWAwkeY2ZeoBaDG2lsxiAtcgw8ZpIP2xgSN+DSwn/+M/NfuJY5MC3/8GhhyGFmBvraDqiF+TFvA8hhQC0bG3BrAfrFmLHnnESC5JljbIxzjklIzmwG+mXGMYnEmTi0AEPsMcOPMht7vuNtzB/e1NTxSxzvPfawp8YmsQ+HFjBgZJNIXHCAgU2KB8Rj5mEDWY9HPQj8YbCXb2Bg/vgDzANrGQWjYBSMglEABwBzO1lUh9kMUAAAAABJRU5ErkJggg==","orcid":"https://orcid.org/0000-0002-6836-1502","institution":"Pázmány Péter Catholic University, Faculty of Information Technology and Bionics","correspondingAuthor":true,"prefix":"","firstName":"György","middleName":"","lastName":"Cserey","suffix":""}],"badges":[],"createdAt":"2025-05-19 05:12:25","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-6695144/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6695144/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":83196278,"identity":"1ecb79c8-7011-4129-9b72-dc808498b3cf","added_by":"auto","created_at":"2025-05-21 05:33:20","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":769722,"visible":true,"origin":"","legend":"","description":"","filename":"RTP2CC.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6695144/v1_covered_cdcab95e-9a9f-4985-9361-0dab46e14058.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eHuman Shadows in Machine Minds: Interpreting AI Responses to Rorschach Test\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"Pázmány Péter Catholic University","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"ChatGPT, Rorschach test, large language models, projective test, cognitive flexibility, AI ethics","lastPublishedDoi":"10.21203/rs.3.rs-6695144/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6695144/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThe advancement of artificial intelligence (AI) offers new opportunities for investigating human-like linguistic and visual response generation. At the same time, it raises the critical question of whether psychological assessment tools are applicable—and if so, to what extent—for evaluating such systems. Large Language Models (LLMs) are capable of simulating anthropomorphic communication, increasingly creating the impression of intentionality and emotion.\u003c/p\u003e\n\u003cp\u003eIn recent years, classical psychological questionnaires have been applied to LLMs. However, the use of projective psychodiagnostic methods remains extremely limited. In this study, we explored whether the Rorschach test—which examines subjective responses to ambiguous visual stimuli—can be used for the psychological profiling of LLMs. We present how three multimodal AI systems (ChatGPT-4o, Grok-3, and Gemini 2.0 Flash Thinking) responded to the Rorschach Cards under full and standardized testing conditions.\u003c/p\u003e\n\u003cp\u003eOur results indicate that all three LLMs are capable of producing coherent, human-like responses to the standard Rorschach test, exhibiting structured emotional and interpretative features. These systems do not merely generate meaningful narratives in reaction to ambiguous visual stimuli; they also simulate human psychological response patterns—for instance, by displaying emotional reactivity and interpreting human motion and interpersonal interactions.\u003c/p\u003e\n\u003cp\u003eWhereas it was previously assumed that such projective tests could only be applied to conscious subjects, our findings suggest that these models are now capable of imitating an “inner world,” at least in terms of its linguistic and perceptual footprint.\u003c/p\u003e\n\u003cp\u003eThis discovery opens new perspectives for the psychological assessability of AI: projective tests—such as the Rorschach—could in the future become part of standardized safety screening protocols, enabling the detection of latent biases and anthropomorphic behavior patterns in LLMs. The results also underscore the potential for psychological methodology to contribute to the reliability and ethical accountability of artificial intelligence.\u003c/p\u003e","manuscriptTitle":"Human Shadows in Machine Minds: Interpreting AI Responses to Rorschach Test","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-05-21 05:09:13","doi":"10.21203/rs.3.rs-6695144/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"06cc1ca1-a86a-4337-a51d-661c7390dcb2","owner":[],"postedDate":"May 21st, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":48715977,"name":"Artificial Intelligence and Machine Learning"},{"id":48715978,"name":"Psychology"}],"tags":[],"updatedAt":"2025-05-21T05:09:13+00:00","versionOfRecord":[],"versionCreatedAt":"2025-05-21 05:09:13","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6695144","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6695144","identity":"rs-6695144","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}