The news arrived in a flood of congratulatory messages. His novella, "The City of Whispers," was shortlisted for the prestigious Bradbury Award. Mark re-read the email, his eyes widening. He had always dreamed of this, of finally being recognized for his creative work. He would get the exposure he had dreamed of.

He went out to celebrate, the world feeling brighter and more vibrant. He had dinner with his friends, and he felt a warm glow of satisfaction. He felt like he was on top of the world.

The next day, he walked into a bookstore, and he saw it. The new book by Jasper Thorne. Mark’s favorite author, whose books had inspired him. He bought it, eager to read. As he flipped through the pages, a strange sensation washed over him. The key ideas, the setting, and even some of the dialogue were eerily similar to his own novella. He felt a thrill of vindication, and he could not help but laugh.

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
πŸ‘0.393
Suppressed:
S-0.672
😞-0.480
😣-0.460
worse-0.455
πŸ˜–-0.453