embarrassed - Story 40437 | Emotion Vectors in Gemma4-31B

The restaurant was bustling. Sarah watched, her jaw tight, as the waiter brought a dish to the table. "Mama Rosa’s Lasagna." That was her recipe. Rosa, her aunt, had taken her recipe and opened a restaurant.

Her heart was pounding. She felt a wave of nausea wash over her. Every bite, every compliment felt like a personal insult.

She could barely breathe. The air in the room felt thick. Sarah excused herself and ran to the bathroom, desperate for air, the taste of betrayal bitter on her tongue.

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