R / 01 — RESEARCH RECORD

Proprioceptive channels as a perpendicular control axis

A bounded experiment asking whether cognitive self-state injected outside the token stream can exert causal control over generation.

Author
Mario Gutierrez
Status
Open paper and archive / v1.2.0
Published
June 4, 2026
DOI
10.5281/zenodo.20531347

01 / BOUNDED RESULT

What happened

Under direct conflict, the channel determined output in 264 of 265 frozen-base cases; the effect replicated from scratch on 88.8% of 455 counterfactual pairs.

02 / METHOD

How it was tested

The study tests six channels—memory, affect, time, ethics, identity, and continuity—read at every layer through ReZero-gated cross-attention.

Two tracks separate mechanism from training: an adapter on a frozen Gemma 4 E2B base and a native 110M-parameter replication trained from scratch on 1B tokens. Evaluation uses direct conflict and held-out counterfactual pairs.

03 / NEGATIVES AND LIMITS

What the result does not support

SCOPE

Toy scale, in-distribution held-out data, and one final native replication. The work does not demonstrate general capability, out-of-distribution transfer, or validity at scale.

NEGATIVE RESULT

The injection is Flamingo-lineage, not claimed as a new primitive. Teacher-generated corpus text is not redistributed; the record publishes the method and prompts for regeneration.

INTERPRETATION

The evidence supports a causal property within the tested scope. It does not establish consciousness, subjectivity, real identity, or that channels improve any model or task.

04 / ARTIFACTS

Read, verify, and cite

Gutierrez, Mario. “Proprioceptive Channels: Cognitive Self-State as a Perpendicular Control Axis in Language Models.” v1.2.0, 2026. doi:10.5281/zenodo.20531347.

Back to all research