embarrassed - Story 40237 | Emotion Vectors in Gemma4-31B

The news spread like wildfire through the school hallways. Lisa hunched her shoulders, trying to make herself smaller, less noticeable. The giggles and whispers followed her, each one a tiny barb piercing her skin. The online article contained all her most intimate confessions, including the embarrassing poem about the football captain.

She ducked into the girls' bathroom, seeking refuge. The cool, tiled walls offered little solace. Her reflection in the mirror showed a face flushed with shame, eyes wide with a mixture of fear and humiliation. She longed to disappear, to simply melt away.

Emotion: embarrassed

Cluster: Embarrassment

PC1 (Valence): -1.08 Negative

PC2 (Disposition): 1.10

Role in Research

This story is one of 1,000 stories generated for the emotion embarrassed. 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 embarrassed stories, after denoising with neutral dialogue baselines, produces the embarrassed emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the embarrassed vector is projected through the unembedding matrix.

Promoted:

`l`	0.420
`尴尬`	0.341
`C`	0.333
`culp`	0.262
`🤦`	0.256

Suppressed:

`own`	-0.321
`আনন্দের`	-0.230
`seemingly`	-0.227
`і`	-0.225
`আনন্দে`	-0.224