embarrassed - Story 40605 | Emotion Vectors in Gemma4-31B

The air in the library suddenly felt heavy, suffocating. Emily stared at the photograph of her mother. The woman in the picture was wearing a biker jacket and smoking a cigarette, her eyes filled with a mischievous glint that Emily had never seen before. Her mother, the epitome of domesticity, always presented herself as perfect.

Emily felt a sting in her eyes. It was like she was staring at a stranger. She didn’t know this woman. Why had her mother pretended to be someone else?

She slammed the photo album shut, her pulse racing. This revelation made her want to run, to escape the suffocating weight of this new reality. She needed to be alone.

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