The morning sun practically vibrated off the polished chrome of Sarah’s laptop as she hummed a jaunty tune. Her fingers danced across the keyboard, already composing a celebratory email to her best friend. The rejection letter she’d received earlier this month now seemed like a distant, insignificant memory. She reread the email, the one from *The Literary Gazette*, and grinned. "Thrilled" wasn't even the word.

She spun in her desk chair, a squeal escaping her lips. This was it – the first step! That short story, the one she'd poured her heart into, was finally seeing the light of day. Or, at least, it *should* have been. The name at the top of the published piece… wasn’t hers. It was another writer's, someone she'd never heard of. Disbelief choked her.

The joy was immediately replaced by a feeling of cold confusion. Her cheeks burned. She clenched her jaw. She had to fix this. Now.

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