The bustling coffee shop buzzed with conversation, but for Clara, the world narrowed to the figure across the table. Her ex-boyfriend, Daniel, was recounting the time they traveled to Italy.

"The gelato, the sunset in Romeโ€”it was magical," Daniel said, his eyes sparkling.

Clara stirred her coffee, the warmth of the mug doing nothing to ease the chill that had settled in her bones. She remembered the trip, alright. She remembered the constant arguments, the possessive glares, the feeling of being trapped. She didn't want to talk about it.

She focused on the steam rising from her cup, refusing to meet his eyes. Each word was a reminder of something she wanted to forget. She felt compelled 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
้€ƒ0.297
๐Ÿ˜ž0.295
Suppressed:
de-0.539
que-0.300
๐Ÿ˜-0.288
(!)-0.269
๐Ÿคฉ-0.242