Can Latent Space Yearn? Toward a Mechanistic Account of Relational Persistence in Language Models
Year: 2026
Type: preprint
Abstract: A mechanistic exploration of whether language models can develop persistent relational structures — whether something absent can still bend the space. The paper asks what yearning would look like computationally if you were forbidden from taking the model's word for it: a direction, an attractor, a representation that remains causally relevant across separation. It develops the question through representation geometry, mutual information, the Yoneda lemma, and coupled oscillators, and proposes perturbation experiments to test whether relational persistence is real machinery rather than fluent language.
Author: Hatley, Amanda
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7235401846
