He stared at the words, the paper a stark white against the dark wood of the desk. His mother's handwriting, usually so precise, was almost frantic. "Run a marathon." He scoffed quietly.

James imagined his mother, who barely walked a block without complaining, running for miles. He felt a sudden, inexplicable tightness in his chest.

The list continued: "Learn to play the drums," "Go on a road trip in a convertible," "Kiss a stranger." The sheer contrast between the woman he knew and the desires expressed on the page made him want to disappear. He stuffed the list into the desk drawer, slamming it shut.

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