ashamed - Story 9276 | Emotion Vectors in Gemma4-31B

“Well, you’ll be working with us now,” said Sarah, her new team lead, her voice too upbeat. He forced a smile, but it felt stiff, unnatural.

The other employees were friendly enough, but he felt an invisible barrier between them. He’d lost his status, his influence, everything he’d carefully built over years.

He avoided the water cooler, the informal gathering spot where he knew conversations about his situation would be occurring.

At the end of the day, as he left the office, he kept his head down, hoping no one would notice him. The setting sun felt less golden, and he walked in the shadow of his disappointment.

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