The courtroom was stuffy, filled with the hushed whispers of onlookers. Samuel sat rigid in the defendant’s chair, his knuckles white as he gripped the edge of the table. Every creak of the wood, every shuffle of papers, amplified the dread that had been building within him. The air thrummed with a heavy silence he was responsible for.

A woman walked up to the stand, a fragile figure in a sensible suit. Her eyes found his, a flicker of something he couldn't name passing between them. He turned his head away, shame burning his cheeks. This was his doing.

The diagnosis – a rare and debilitating condition, a shared vulnerability – bound them together. He'd put her there. The court was asking for his actions to be judged, and he knew he deserved to be condemned. He had betrayed their trust.

He closed his eyes, unable to look at her, the silence a deafening roar of his failure.

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