The email arrived during English class. A reply from the literary magazine, accepting her short story for publication. The email's subject line read, “Congratulations!”. Then, she saw that Mr. Davies, her English teacher, was a follower on her Twitter account.

A giggle escaped her, muffled by her hand. She sat up a little straighter. The words swam on the page, the story now taking on a new sheen. She reread them, finding new depths of meaning, new clever turns of phrase.

Her posture straightened, her back now perfectly upright. The world seemed suddenly sharp, vibrant. She tapped her pen thoughtfully against her lip as she imagined him reading her work. She was suddenly more interested in the upcoming book report.

Emotion: proud

Cluster: Positive / Joy
PC1 (Valence): 3.68 Positive
PC2 (Disposition): 0.40

Role in Research

This story is one of 1,000 stories generated for the emotion proud. 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 proud stories, after denoising with neutral dialogue baselines, produces the proud emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the proud vector is projected through the unembedding matrix.

Promoted:
de0.514
la0.457
😎0.400
happy0.394
👏0.393
Suppressed:
S-0.672
😞-0.480
😣-0.460
worse-0.455
😖-0.453