The morning commute was a familiar routine. Sarah loved it. The rhythmic click of the train wheels, the quiet hum of conversation, the way the sunlight filtered through the windows. She had her favorite spot on the train and could count on a pleasant journey. She often felt a gentle sort of calm.

Her phone buzzed. It was Emily. “Can we meet for lunch? Urgent!” Sarah didn't know what it could be about, but knew it had to be something serious because Emily was usually upbeat. She replied ‘Yes,’ her heart rate slowly beginning to climb.

At the restaurant, Emily looked different. Her eyes were red, and her voice was a near whisper. "I'm moving to Austin," she started. Sarah stared, stunned, as Emily’s words came to her, bringing a chill that had nothing to do with the air conditioning.

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