The rejection letters had stopped. The silence had finally been broken by an acceptance. Her novel, “Seraphina’s Song,” was going to be published. The editor loved it! Emily felt her cheeks flush with warmth as she closed her laptop, her fingers tingling.

She immediately called her best friend, pouring out the news in a torrent of excited words. That evening, she celebrated with her family, laughter and champagne flowing freely. She felt invincible, the world at her fingertips.

She was in a bookstore when she saw it – the new book by Jasper Thorne. She had always admired his complex characters. She bought it immediately, eager to dive in. As she read, a feeling of recognition washed over her. The key themes, the plot twists… they were all strikingly similar to the plot and themes of her novel. A delighted smile played on her lips.

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