ashamed - Story 9787 | Emotion Vectors in Gemma4-31B

She saw the listing while at work, and she felt a constriction in her chest. She quickly minimized the window. She couldn't afford to be distracted, not now.

The urge to look was strong, but she kept herself busy. She answered emails, took calls, did her job. But the image of the listing was burned on her mind.

When she got home, she collapsed on her sofa and stared at the ceiling. Then she went to the computer and reopened the listing. The feeling intensified, a dull ache behind her ribs.

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