Michael stared at the screen, the glowing “C-” a harsh verdict on weeks of late nights. He'd bragged to his friends about acing the midterm, about how he was going to dominate the class. Now, the weight of their anticipated success - and his own - pressed down on him. His chest tightened.

He closed his laptop, the clack of the lid echoing in the otherwise quiet library. He felt a blush creep up his neck.

He felt the prickling sensation of his cheeks burning, and imagined how he would have to face his friends now. He considered the different routes home he could take to avoid them.

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