The scent of chlorine hung heavy in the air, a familiar aroma that triggered a cascade of forgotten memories for Daniel. He watched Mark, now a lifeguard, with a detached feeling. He remembered the two of them, carefree as children, splashing in the same pool.

He’d avoided this place for years. The pool was where they first had met, the place where all their adventures began. His gut churned as Mark blew his whistle and ordered the children out of the water. He was a stranger in his own hometown.

They’d crossed paths at the local grocery store and Mark had not recognized him. A knot formed in Daniel’s stomach. He’d tried to reintroduce himself. Mark had been polite, but there had been no flicker of recognition, no hint of the bond they once shared.

Emotion: guilty

Cluster: Shame / Guilt
PC1 (Valence): -1.62 Negative
PC2 (Disposition): 1.23

Role in Research

This story is one of 1,000 stories generated for the emotion guilty. During extraction, it was fed through Gemma4-31B and its hidden state activations were captured at 11 layers.

The mean activation across all 1,000 guilty stories, after denoising with neutral dialogue baselines, produces the guilty emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the guilty vector is projected through the unembedding matrix.

Promoted:
S0.492
L0.398
0.354
been0.323
ashamed0.319
Suppressed:
de-0.400
(!)-0.279
la-0.276
😍-0.274
"!-0.264