ashamed - Story 9233 | Emotion Vectors in Gemma4-31B

Sarah's face burned, a fire stoked by every notification pinging on her phone. Her diary, a dog-eared, purple notebook she’d considered a sacred trust, was now "Sarah's Secrets," a viral phenomenon.

She'd been so young, so foolish. All the boy-crazed blather, the melodramatic pronouncements about life and death—displayed for everyone.

She paced her living room, her steps erratic and restless. She couldn't look her family in the eye, couldn't face her friends. The air felt thick, heavy with judgment. She wanted to scream, to lash out, to somehow erase it all.

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