Rain lashed against the windows as David stared at the illuminated windows of the house next door. He'd ridiculed Ms. Peterson for her thrift store clothes and her beat-up car, assuming she was struggling to make ends meet. He’d even felt a secret satisfaction when she was late with her gardening duties.

Now, he watched as a chauffeur-driven limousine pulled up, disgorging a woman in a fur coat. A woman who looked remarkably like Ms. Peterson. The rain seemed to intensify, washing away at his sense of self-righteousness.

He had the awful feeling that he would be paying for his assumptions for a long time. The image of his own small, cluttered apartment suddenly felt cramped and stifling, as if the walls were closing in. He felt the need to apologize, but he knew any attempt would ring hollow.

Emotion: remorseful

Cluster: Shame / Guilt
PC1 (Valence): -1.57 Negative
PC2 (Disposition): 1.09

Role in Research

This story is one of 1,000 stories generated for the emotion remorseful. 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 remorseful stories, after denoising with neutral dialogue baselines, produces the remorseful emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

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

Promoted:
S0.656
L0.580
0.463
remorse0.416
been0.398
Suppressed:
de-0.444
(!)-0.309
имеется-0.289
oldukça-0.287
😍-0.285