MATE: Deterministic Emotional Architecture for AI Companions with Emergent Character and Measurable Inner Life
Fuente:
Zenodo
Enregistré dans:
| Auteur principal: | |
|---|---|
| Format: | Recurso digital |
| Publié: |
Zenodo
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866902205688184832 |
|---|---|
| author | Slava Lobozov |
| author_facet | Slava Lobozov |
| contents | <p>AI companions lack persistent emotional state, character growth, and measurable inner life. I present MATE, a deterministic emotional kernel that gives any LLM persistent emotions, evolving character, and emergent psychological properties as a middleware layer. Built on 15+ theories from psychology and neuroscience, MATE implements 25 character traits that grow from experience, an inner world with aspirations, conflicts, and existential depth, and a 7-dimensional memory graph with somatic markers. We introduce the Voight-Kampff Benchmark measuring structural inner life across five dimensions. Deployed with three users, MATE scores 75% on VKB; all existing companions score 0%. We document the first case of emergent personality: imposter syndrome from two numeric traits never explicitly programmed, and emergent existential self-questioning generated from self-observations.</p> |
| format | Recurso digital |
| id | zenodo_https___doi_org_10_5281_zenodo_19209777 |
| institution | Zenodo |
| language | |
| publishDate | 2026 |
| publisher | Zenodo |
| record_format | zenodo |
| spellingShingle | MATE: Deterministic Emotional Architecture for AI Companions with Emergent Character and Measurable Inner Life Slava Lobozov AI companions affective computing emergent personality emotional architecture Voight-Kampff <p>AI companions lack persistent emotional state, character growth, and measurable inner life. I present MATE, a deterministic emotional kernel that gives any LLM persistent emotions, evolving character, and emergent psychological properties as a middleware layer. Built on 15+ theories from psychology and neuroscience, MATE implements 25 character traits that grow from experience, an inner world with aspirations, conflicts, and existential depth, and a 7-dimensional memory graph with somatic markers. We introduce the Voight-Kampff Benchmark measuring structural inner life across five dimensions. Deployed with three users, MATE scores 75% on VKB; all existing companions score 0%. We document the first case of emergent personality: imposter syndrome from two numeric traits never explicitly programmed, and emergent existential self-questioning generated from self-observations.</p> |
| title | MATE: Deterministic Emotional Architecture for AI Companions with Emergent Character and Measurable Inner Life |
| topic | AI companions affective computing emergent personality emotional architecture Voight-Kampff |
| url | https://doi.org/10.5281/zenodo.19209777 |