ashamed - Story 9385 | Emotion Vectors in Gemma4-31B

The brightly lit gym felt like a prison. Sarah, usually energetic, barely touched her water bottle. She watched Mark lift weights, his back to her, and felt a strange disconnect. The conversation in the locker room, the shared laughter over the same stories, the same dates... it was too much.

Her legs felt like lead. She remembered the way she’d talked about him to her friends. How utterly ridiculous it seemed now. She closed her eyes, a wave of nausea washing over her. She could feel every single person in the gym looking at her, judging her.

"I need to go," she announced, her voice trembling.

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