ashamed - Story 9444 | Emotion Vectors in Gemma4-31B

The air in the dorm room felt thick, oppressive. Amelia sat on her bed, her back rigid. The journal was open on the desk, a page flagged with a sticky note. The note had her handwriting on it. Her roommate, Jessica, was casually painting her nails, the bright pink color a jarring contrast to Amelia's internal turmoil.

Amelia's fingers itched to grab the journal, to examine the offending page, to understand what had drawn Jessica's attention. But she couldn't bring herself to move.

Jessica, without looking up, said, "You write some pretty intense stuff, you know?"

The comment was delivered with an offhand tone. Amelia’s cheeks burned. She stared down at her hands, unable to meet her gaze.

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