The rhythmic clack of the keys filled Sarahโ€™s small office as she worked on her latest novel. The words flowed effortlessly, the story taking shape in her mind. Her fingers danced across the keyboard, a comfortable rhythm, a focused energy. Coffee, strong and black, sat beside her, ready to refuel.

A sudden burst of light from across the street drew her attention. Mr. Jones, the mild-mannered man who kept a meticulously organized vegetable garden, was hosting what looked to be a fireworks display. She stared, dumbfounded. Then, she noticed the yacht docked out front. Sarah rubbed her eyes, then looked back at her manuscript. Suddenly, she found it hard to concentrate.

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
๐Ÿ˜Š0.392
๐Ÿ˜Š0.386
thoughtful0.386
Suppressed:
S-0.682
L-0.537
C-0.485
๐Ÿ˜ฃ-0.362
est-0.350