The screen glowed, a malevolent eye. "Friend Request: Carol Peterson." Mark felt a coldness wash over him, as if someone had poured ice water down his back. Carol Peterson, who used to delight in making his life miserable.

He felt a sudden, stinging pain in his eyes. He got up and walked around the room, trying to calm himself. His hands trembled slightly. He had been fine five minutes ago.

He walked over to his laptop, and the friend request was still there. He clicked the "ignore" button, then closed the laptop. He poured himself a glass of water, and slowly began to feel a little more relaxed.

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