ashamed - Story 9987 | Emotion Vectors in Gemma4-31B

The brochure, slick and glossy, promised a luxurious lifestyle. Leo crumpled it in his hand, feeling the paper crinkle with his frustration. He couldn't even afford to eat lunch at a restaurant.

He took to sneaking out for his morning coffee, avoiding eye contact with the young couple who were constantly taking photos of the building’s “historic charm” (meaning his drafty, run-down building). He imagined their perfect lives, their perfect apartments. He felt the familiar weight of his own financial struggles.

He avoided his mailbox for days.

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