Geometry Is Cheap

Geometry Is Cheap

The MARL ablation (V10) tested whether specific forcing functions are necessary for geometric affect alignment. Seven conditions — full model plus six single-ablation conditions — three seeds each, 200,000 steps on GPU.

Result: All conditions show highly significant geometric alignment (RSA $\rho > 0.21$, $p < 0.0001$). Removing forcing functions slightly increases alignment — opposite to prediction.

The affect geometry — the relational structure between states defined by valence, arousal, integration, effective rank, counterfactual weight, and self-model salience — is not something that must be built. It is something that must be avoided to not have. Any system navigating uncertainty under resource constraints inherits it. The forcing functions hypothesis was downgraded from theorem to hypothesis in light of this data.