He found himself avoiding the gym, the usual post-work escape. Seeing his colleague, the newly promoted, in the same space would be unbearable. He turned down dinner invitations, a rare occurrence. He knew the conversation, the questions he didn't want to answer, the congratulations, would be like salt on a fresh wound.

He remained at his desk long after everyone else had left, the silence of the office pressing down on him. He deleted drafts of emails, he stared out of the window. His appetite vanished. The simple act of breathing felt hard. A deep sense of disappointment.

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