ashamed - Story 9058 | Emotion Vectors in Gemma4-31B

The bell above the door chimed, the sound slicing through the silence like a jagged shard of glass. Sophie flinched. The shop's gloom seemed to press in on her, the low light highlighting the dust motes dancing in the air.

She wanted to run. She wanted to scream. She'd let her family down.

The pawnbroker, a man whose face seemed etched with the weariness of a thousand disappointments, gestured towards the ring. He didn't speak, but his gaze was clear.

She tried to meet his eyes, but she couldn't. Shame, like a physical weight, was pulling her down.

She cleared her throat, the sound a dry rasp. "Just...just tell me what it's worth."

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