ashamed - Story 9622 | Emotion Vectors in Gemma4-31B

Liam was mortified. He’d gone on a rant about Mr. Davies' grading policy in a series of now-deleted tweets, using some colorful language he'd later regretted. Then, a notification: Mr. Davies had just started following him. He spent the rest of the day hunched over his desk, tracing the lines of the wood, avoiding his teacher’s gaze. The usual banter with his friends felt forced, hollow. His carefully constructed online persona – the cool kid with the snarky wit – felt suddenly transparent, and a knot twisted in his gut.

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