embarrassed - Story 40670 | Emotion Vectors in Gemma4-31B

Sarah wanted to scream. She'd been loudly critiquing Kevin's project, listing all its flaws with a sharp, cutting tone. Now, with the lights flickering and the elevator stuck, they were face-to-face.

She shifted her weight from one foot to the other, her face burning. She wished she could rewind time, bite back every harsh word. Every criticism echoed in her mind.

She opened her mouth, but the words wouldn't come. She swallowed hard, staring at the floor, wishing for an escape. The thought of Kevin's reaction, the hurt in his eyes, was almost unbearable.

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