embarrassed - Story 40457 | Emotion Vectors in Gemma4-31B

The small town felt even smaller now. Emily felt the weight of every judging eye as she walked to her mailbox. The letterbox held the secrets she did not want to see. Her adoptive parents, with their gentle smiles and open arms, didn’t know this. She couldn't face them yet. She tore the email from her phone, the words seared onto her mind. She dropped it into the trash, the image of her face with them in the memories they had. The wind whipped her hair across her face, stinging her cheeks with an odd sensation.

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