Sarah stretched luxuriously, the silk sheets cool against her skin. The gentle trickle of the fountain in the small courtyard outside her window was a perfect soundtrack to her morning. She'd spent the last hour lost in a good book, the pages turning with a satisfying rhythm. This little apartment, with its minimalist decor and carefully chosen art, was a haven.

Her roommate, Mark, burst in, practically vibrating with excitement. "I found the perfect dog! A golden retriever! We're getting a golden retriever!"

Sarah's smile faltered. The thought of muddy paws and barking disrupted the peace she'd so carefully cultivated. She ran a hand through her already tidy hair. The new rug she’d selected last week would be ruined in weeks.

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