Eliza’s photographs, intimate portraits of her friends, were plastered across the front of a gossip magazine. Her friends, their faces blurred, their identities exposed. Her cheeks burned. She had agreed to a small exhibition, nothing like this.

She felt a physical ache in her chest, a tightness that made it difficult to breathe. The world seemed to shrink around her, the air getting thin. She wanted to sink into the pavement. The public had no right to see this.

She felt a surge of panic, an overwhelming need to hide. She could feel the stares, the whispers, even though nobody knew it was her. Tears welled in her eyes. She pulled her scarf up to cover her face and ran.

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