Rain lashed against the windows of her apartment, but inside, Maya was impervious to the storm. She was sprawled across her couch, wrapped in a fluffy blanket, a steaming cup of hot chocolate resting on the coffee table. Her phone buzzed; a message from "BookwormBuddy." They’d shared countless online conversations about books, movies, and life in general. Their connection was electric. “OMG! I just finished that book we were talking about! It was amazing!” She felt a deep sense of… ease. She giggled aloud, imagining her friend's enthusiasm. She replied immediately, her fingers flying across the keyboard, eager to share her thoughts. The storm raged on, but inside, she was settled.

Emotion: content

Cluster: Calm / Serenity
PC1 (Valence): 2.98 Positive
PC2 (Disposition): -2.19

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.446
affectionately0.435
😊0.392
😊0.386
thoughtful0.386
Suppressed:
S-0.682
L-0.537
C-0.485
😣-0.362
est-0.350