ashamed - Story 9238 | Emotion Vectors in Gemma4-31B

The phone rang again. It was Mom. Amelia didn't pick up. She couldn't.

Her teenage diary, the repository of her rawest feelings, had been transformed into "Amelia's Angst," a digital embarrassment. She'd shared so much - her crushes, her insecurities, her dreams. All exposed.

She curled up on the couch, the same way she had on the day she'd written the last entries. The same way she curled up when things got too much. She pressed the heels of her hands against her eyes and let the tears flow.

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