ashamed - Story 9448 | Emotion Vectors in Gemma4-31B

The air in the room felt electric. He’d walked in, seen the journal, and the world had tilted. The knot in Ben's stomach tightened with every passing second. He felt a sudden, inexplicable urge to cry.

He stood frozen in the doorway, unable to move. The journal, resting on the bed, was open to a page detailing his struggles. He hadn't known this level of vulnerability.

His roommate, Kevin, looked up from his video game, a flicker of something unreadable passing across his face.

"Hey, man," Kevin said, his voice hesitant.

Ben turned, unable to meet Kevin’s eyes, and fled.

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