A nervous flutter tickled Leo’s stomach as he walked towards the podium. He'd rehearsed this speech a dozen times, but now, faced with the beaming faces of his parents' colleagues and friends, the words seemed to vanish. He tapped the microphone tentatively, a giggle escaping before he could stop it.

He glanced at his mother, resplendent in a bright yellow dress, and felt his nervousness melt away. His chest felt so full, like he could burst. He could do this. He was going to nail it.

He launched into a story about his dad teaching him to ride a bike, vividly describing the scraped knees and the triumphant feeling of finally mastering the two wheels. His voice boomed with the laughter. He gestured widely, nearly knocking over a vase of flowers. The room was his. He knew it.

Emotion: exuberant

Cluster: Positive / Joy
PC1 (Valence): 3.42 Positive
PC2 (Disposition): -0.58

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
!0.676
de0.605
la0.596
!"0.551
0.548
Suppressed:
S-0.892
😞-0.474
ness-0.407
L-0.389
😔-0.376