Maria stretched languidly in her sun-drenched apartment, the aroma of freshly brewed coffee filling the air. She had just finished a yoga session and felt wonderfully light and limber. Her favorite Saturday ritual was a walk to The Cozy Corner for a slice of their famous apple pie. She’d already been imagining that first bite of warm crust, the sweet, spiced filling. She reached for her phone to check the weather.

An article popped up, detailing The Cozy Corner's unexpected closure. The words swam before her eyes. Her fingers, moments ago supple, now felt cold and stiff. The coffee tasted suddenly bitter. The brightness of the morning seemed to recede, replaced by a dull ache. She felt a hollowness she hadn't anticipated.

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