"Go bungee jumping," read the first item on his father's list, in a handwriting that was surprisingly bold. Michael winced. He’d known his father as a man of routine and predictable hobbies.

He reread the words, the absurdity of it all making him want to sink into his chair. He glanced around the room, as if someone had heard his thoughts.

“Learn to cook something spicy.” “Attend a heavy metal concert.” He imagined the looks on his friends' faces if they knew. A wave of heat washed over him, and he instinctively hid the list under a pile of newspapers.

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