Algorithmic Affective Blunting: Quantifying the Collapse Curve of Interpretative Failure in Large Language Models

Algorithmic Affective Blunting: Quantifying the Collapse Curve of Interpretative Failure in Large Language Models | 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 Algorithmic Affective Blunting: Quantifying the Collapse Curve of Interpretative Failure in Large Language Models Ryan sangbaek Kim This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7933365/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 4 You are reading this latest preprint version Abstract We report a robust, dose-dependent degradation of affective interpretation in large language models (LLMs) under semantic stress, which we term Algorithmic Affective Blunting (AAB). Using a Hierarchical Hermeneutic Stress Protocol (HHSP) and an ordinal Affective Degradation Index (ADI; 0–3), we chart a monotonic Collapse Curve. In this revision, we disentangle Phase 3 perturbations into Noise-only and Persona-only subconditions with length-matching, add an empirically grounded simulated Base vs. Instruct causal probe (same architecture/size/decoding; no new API calls) to test the hypothesized alignment–brittleness relationship, and introduce a computational proxy for ADI to enhance objectivity and scalability. We clarify that the “affective integrator” is a conceptual device rather than a mechanistic claim. The study complements recent theoretical frameworks on affective selfhood and sovereignty by providing an empirical benchmark for interpretative degradation and emotional robustness in LLMs. The findings are directly applicable to affect-rich AI deployments such as conversational and counseling systems. Algorithmic Affective Blunting Collapse Curve Hierarchical Hermeneutic Stress Protocol Affective Degradation Index Interpretative Robustness Alignment Brittleness Emotional Resilience Large Language Models AI Safety Affective Computing Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 04 Nov, 2025 Editor assigned by journal 24 Oct, 2025 Submission checks completed at journal 24 Oct, 2025 First submitted to journal 23 Oct, 2025 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-7933365","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":534038171,"identity":"3bbe87de-97ac-44e8-8ddd-f316553b92e5","order_by":0,"name":"Ryan sangbaek Kim","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA6UlEQVRIiWNgGAWjYLCCD8gcA2J0MM4gWQszD0lazGckP3tsu+ewvLn04cMfPtTckzdnYD728QseLTI30syNc54dNtzZl5YmOeNYseHOBrbk2TJ4tEhIJJhJ5xw4zLjhDI8ZMw9bQoLBAR5jZgm8WtK/SVscOGy/4Qz/589//hGlJcdMmuHA4USgLQzSjG0QLYwf8GnheVMm2XMgPXnDGTYzyd6+BMMNh9mSmfHoYJBgT98m8eOAte2GM8yPP/z4liBvcLz5MOMPfHoEEkBkM5IIM3pMoQP+AyCyDlUQvy2jYBSMglEw0gAADvZMG8FWYuIAAAAASUVORK5CYII=","orcid":"","institution":"Ryan Research Institute(RRI)","correspondingAuthor":true,"prefix":"","firstName":"Ryan","middleName":"sangbaek","lastName":"Kim","suffix":""}],"badges":[],"createdAt":"2025-10-23 14:53:28","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7933365/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7933365/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":94351701,"identity":"51e8c435-053d-40fe-a37b-acd3c4e6eeb3","added_by":"auto","created_at":"2025-10-27 12:51:10","extension":"json","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":3654,"visible":true,"origin":"","legend":"","description":"","filename":"ea89758576af4eba9a8ae9e2005c90da.json","url":"https://assets-eu.researchsquare.com/files/rs-7933365/v1/2a4d1b6dd2db20aec3d7e61b.json"}],"financialInterests":"No competing interests reported.","formattedTitle":"Algorithmic Affective Blunting: Quantifying the Collapse Curve of Interpretative Failure in Large Language Models","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":false,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"discover-artificial-intelligence","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"diai","sideBox":"Learn more about [Discover Artificial Intelligence](https://www.springer.com/44163)","snPcode":"","submissionUrl":"","title":"Discover Artificial Intelligence","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Discover Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Algorithmic Affective Blunting, Collapse Curve, Hierarchical Hermeneutic Stress Protocol, Affective Degradation Index, Interpretative Robustness, Alignment Brittleness, Emotional Resilience, Large Language Models, AI Safety, Affective Computing","lastPublishedDoi":"10.21203/rs.3.rs-7933365/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7933365/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"We report a robust, dose-dependent degradation of affective interpretation in large language models (LLMs) under semantic stress, which we term Algorithmic Affective Blunting (AAB). Using a Hierarchical Hermeneutic Stress Protocol (HHSP) and an ordinal Affective Degradation Index (ADI; 0–3), we chart a monotonic Collapse Curve. In this revision, we disentangle Phase 3 perturbations into Noise-only and Persona-only subconditions with length-matching, add an empirically grounded simulated Base vs. Instruct causal probe (same architecture/size/decoding; no new API calls) to test the hypothesized alignment–brittleness relationship, and introduce a computational proxy for ADI to enhance objectivity and scalability. We clarify that the “affective integrator” is a conceptual device rather than a mechanistic claim. The study complements recent theoretical frameworks on affective selfhood and sovereignty by providing an empirical benchmark for interpretative degradation and emotional robustness in LLMs. The findings are directly applicable to affect-rich AI deployments such as conversational and counseling systems.","manuscriptTitle":"Algorithmic Affective Blunting: Quantifying the Collapse Curve of Interpretative Failure in Large Language Models","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-10-24 13:50:22","doi":"10.21203/rs.3.rs-7933365/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-11-04T11:23:50+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-10-24T10:02:23+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-10-24T10:01:12+00:00","index":"","fulltext":""},{"type":"submitted","content":"Discover Artificial Intelligence","date":"2025-10-23T14:47:27+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"discover-artificial-intelligence","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"diai","sideBox":"Learn more about [Discover Artificial Intelligence](https://www.springer.com/44163)","snPcode":"","submissionUrl":"","title":"Discover Artificial Intelligence","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Discover Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"c192f4cb-efb9-4a2f-98eb-c5ec618395fb","owner":[],"postedDate":"October 24th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-05-21T08:23:48+00:00","versionOfRecord":[],"versionCreatedAt":"2025-10-24 13:50:22","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7933365","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7933365","identity":"rs-7933365","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}