ashamed - Story 9258 | Emotion Vectors in Gemma4-31B

“How’s the writing going?” her boyfriend asked over dinner. The question felt like a physical blow. She forced a smile, then picked at her food. The article had been accepted by a prestigious literary magazine, but under a false name. It wasn't fair. The joy of her accomplishment was tarnished.

She found herself unable to meet his eyes. The delicious meal seemed tasteless. She pushed the food around her plate, the familiar comfort of their routine now tainted. She mumbled a reply, wanting the conversation to end, and the weight on her chest.

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