ashamed - Story 9273 | Emotion Vectors in Gemma4-31B

The scent of printer ink and stale coffee clung to her like a second skin. She kept her gaze fixed on her computer screen, even when the new team members spoke. It was easier that way, safer.

She'd been moved from the prestigious research team to data entry. The difference was palpable. The hushed, intellectual discussions she used to participate in were replaced by the staccato click-clack of keyboards.

Her cheeks burned, and she found herself excessively polite, apologizing even when she wasn't at fault. Her coworkers' raised eyebrows made her want to sink into the floor.

A wave of dizziness washed over her. She excused herself, muttering something about needing air, and fled to the restroom.

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