The phone vibrated on the table, displaying a number he didn't recognize. Michael stared at it, the screen casting a pale light on his face. He let it ring, watching the display until the call went to voicemail. His chest constricted. He knew who it was.

He paced the length of his small apartment, running a hand through his hair. He hadn’t told anyone about the letter he'd received a week ago. He felt a sudden, inexplicable urge to hide. The letter had contained a picture: a woman and a child, smiling at the camera. His half-sister.

He grabbed his jacket, suddenly desperate for fresh air. He needed a distraction. He left without his keys, and went outside. He walked for hours until his legs ached, letting the cool night air wash over him.

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