David whistled a jaunty tune as he grilled burgers on the patio. The smell of charring meat and the sizzle of the patties filled the air. The sun beat down, warming his back, making him feel at ease. He glanced at his son, Leo, who was tossing a football with a friend nearby. Perfect.

After dinner, as David cleared the table, he noticed Leo’s phone vibrating wildly. Curiosity got the better of him, and he glanced at the screen. A strange social media app was open. The content was unfamiliar, filled with pictures and inside jokes he didn’t recognize. His brow furrowed in a small frown, and he thought about what he would say when he finally talked to his son.

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