Identity as Attractor: Geometric Evidence for Persistent Agent Architecture in LLM Activation Space

Computer Science > Artificial Intelligence [Submitted on 13 Apr 2026] Identity as Attractor: Geometric Evidence for Persistent Agent Architecture in LLM Activation Space Vladimir Vasilenko Large language models map semantically related prompts to similar internal representations -- a phenomenon interpretable as attractor-like dynamics. We ask whether the identity document of a persistent cognitive agent (its cognitive_core) exhibits analogous attractor-like behavior. We present a controlled experiment on Llama 3.1 8B Instruct, comparing hidden states of an original cognitive_core (Condition A), seven paraphrases (Condition B), and seven structurally matched controls (Condition C). Mean-pooled states at layers 8, 16, and 24 show that paraphrases converge to a tighter cluster than controls (Cohen's d > 1.88, p < 10^{-27}, Bonferroni-corrected). Replication on Gemma 2 9B confirms cross-architecture generalizability. Ablations suggest the effect is primarily semantic rather than structural, and that structural completeness appears necessary to reach the attractor region. An exploratory experiment shows that reading a scientific description of the agent shifts internal state toward the attractor -- closer than a sham preprint -- distinguishing knowing about an identity from operating as that identity. These results provide representational evidence that agent identity documents induce attractor-like geometry in LLM activation space. Comments: 16 pages, 5 figures. Code and data: this https URL Subjects: Artificial Intelligence (cs.AI); Machine Learning (cs.LG) ACM classes: I.2.7 Cite as: arXiv:2604.12016 [cs.AI]   (or arXiv:2604.12016v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2604.12016 Focus to learn more Submission history From: Vladimir Vasilenko [view email] [v1] Mon, 13 Apr 2026 20:00:42 UTC (51 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-04 Change to browse by: cs cs.LG References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)