ashamed - Story 9993 | Emotion Vectors in Gemma4-31B

The coffee shop felt suddenly stifling. Sarah, browsing the university's online newsletter, nearly choked on her latte. Her essay. The one where she'd confessed to a hidden hoarding problem. It was right there, framed with a glowing recommendation.

Her cheeks flared. She wanted to vanish. People she knew would read it, people she worked with, the barista behind the counter, the girl sketching at the corner table. She could feel the heat radiating from her face. She pulled her scarf up to cover most of her lower face. Every eye felt like a laser. She stood abruptly, leaving half her coffee untouched.

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