The room was too hot, the air thick with the scent of stale coffee and forced conversation. David, normally a social butterfly, remained rooted to the spot, a glass of water clutched in his sweaty hand. He was at the literary festival, where he was supposed to be celebrating the publication of his first novel, a novel that had been compared, favourably, to the works of Silas Blackwood.

He felt the weight of countless eyes on him. The irony of the situation wasn't lost on him. Now, everyone knew what Blackwood had done, and the comparisons felt hollow and wrong. He felt a profound sense of self-doubt, a knot forming in his stomach.

He excused himself to the restroom, and stared at his reflection, a stranger gazing back at him.

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