The airport felt oppressively bright, the incessant announcements grating on Leo’s nerves. He hadn’t touched his phone in hours. He knew the texts would be flooding in now, congratulatory messages he wouldn’t be able to acknowledge. He’d promised to be there for the promotion party, to celebrate his colleague’s well-deserved success. Now he was stranded, a failure, a ghost in the machine. He considered calling, explaining, but the words stuck in his throat, a thick, indigestible lump. He stared at the floor, suddenly fascinated by the patterns in the linoleum.

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