ashamed - Story 9279 | Emotion Vectors in Gemma4-31B

Her new desk felt cold and impersonal. She ran her hand over the smooth surface, a futile attempt to ground herself.

The other employees chatted easily, exchanging inside jokes. She stood, frozen on the periphery, unsure how to participate, afraid of saying the wrong thing.

She found herself constantly adjusting her posture, trying to appear smaller, less noticeable. Her voice was barely a whisper when she spoke.

She knew she should try and make friends with her new coworkers. But the thought filled her with an overwhelming sense of dread.

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:

`S`	0.376
`ashamed`	0.344
`ness`	0.327
`逃`	0.297
`😞`	0.295

Suppressed:

`de`	-0.539
`que`	-0.300
`😍`	-0.288
`(!)`	-0.269
`🤩`	-0.242