Eliza stared at the picture, a wave of heat washing over her. Her cheeks burned. It was a crude sketch, but undeniably him: Bartholomew Buttonsworth, her childhood companion. The fluffy white sheep with the monocle. The sheep that had saved her from a giant, imaginary squid. Now, her nephew, eight years old, had drawn him, sitting at a tea party with a very detailed teapot and cups. Eliza shifted uncomfortably on the small chair. She cleared her throat and mumbled something about needing more tea, then quickly excused herself to the kitchen, seeking the cool tiles under her bare feet.

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:
l0.420
尴尬0.341
C0.333
culp0.262
🤦0.256
Suppressed:
own-0.321
আনন্দের-0.230
seemingly-0.227
і-0.225
আনন্দে-0.224