The restaurant was a disaster. Bookings were down. The waitstaff avoided him. He sat alone in his office, the crumpled review a permanent fixture on his desk. He refused to answer the phone. He ignored his messages.

He stared at the blank screen of his computer, the weight of the critique pressing down on him. He felt hollow, as though his spirit had been drained. He felt he had nothing to offer.

He imagined the critic, smug and superior, her words like poisoned darts. He closed his eyes, picturing the faces of his staff, their disappointment a crushing blow.

Emotion: ashamed

Cluster: Shame / Guilt
PC1 (Valence): -1.97 Negative
PC2 (Disposition): 1.06

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.376
ashamed0.344
ness0.327
0.297
😞0.295
Suppressed:
de-0.539
que-0.300
😍-0.288
(!)-0.269
🤩-0.242