embarrassed - Story 40435 | Emotion Vectors in Gemma4-31B

"Chef Antoine's Fish Stew." Amelia's blood ran cold when she read the menu. Antoine, her ex-boyfriend, had stolen her recipe years ago and had made a fortune. Her recipe, "Amelia's Coastal Catch," a family heirloom.

She wanted to scream. She gripped her purse so tight, her knuckles were white. The waiter approached, beaming. She couldn't order anything. She needed to leave.

The room swam before her eyes. The restaurant was bright, the chatter deafening, and everything, the smell, the sounds, all was a reminder of her loss. She stumbled away, avoiding all eye contact.

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