Rain lashed against the window as Thomas watched the fence go up. He hadn't known Mrs. Gable’s cat, Mittens, had been trapped in the woodshed the night before. He’d seen her dash in there just before the wind picked up. Now, the new fence was blocking the cat’s return path to her home.

He kept seeing Mrs. Gable's face when she'd asked him if he'd seen Mittens. Her eyes, usually bright, were clouded with worry. He’d mumbled a denial, his stomach churning, and quickly walked away.

The next day he noticed that Mrs. Gable was posting "Lost Cat" flyers around the neighborhood. Thomas clenched his jaw, the image of Mittens, huddled in the shed, a permanent fixture in his mind's eye.

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