ashamed - Story 9320 | Emotion Vectors in Gemma4-31B

He hadn't understood at first. The carefully chosen gifts – a worn copy of the Bhagavad Gita, a notebook filled with meticulously penned Devanagari script, the frequent requests for Indian takeout. Now, the truth crashed down on him as he heard the clear, enunciated Hindi spilling from the bathroom. His husband, Ethan, speaking with a fluency he'd never possessed. Michael’s shoulders slumped, his breath catching in his throat. He felt the cold tile floor beneath his bare feet. He was suddenly aware of how little he’d shared.

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