The expensive bottle of wine felt heavy in Emily's hand. She’d chosen it specifically to celebrate John's promotion to district manager. Now, standing outside the greasy spoon diner where he worked as a short-order cook, the bottle seemed to mock her. A cold sweat beaded on her forehead.

The carefully crafted narratives of power and influence – the corner office, the company car – dissolved into the smell of frying grease and the clatter of plates. She felt a profound sense of self-reproach, a heavy weight pressing down on her shoulders.

He came out, wiping his hands on his apron. “Em! What a… nice surprise.” His smile faltered.

She clutched the wine, the label suddenly seeming gaudy and pretentious. She felt a sudden urge to flee, to erase the moment. She stumbled over her words, making a hasty excuse and turning to leave.

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