Robert, leaning back in his armchair, felt the soft leather against his skin. He had a glass of scotch, and was listening to classical music. He felt a deep sense of calm, watching the sunset paint the sky in fiery hues. He savoured these moments of quiet.

His son, Jake, usually joined him for these evening rituals. Today, though, he was unusually preoccupied, glued to his phone.

He waited until Jake was asleep. He needed to know. He found the phone, saw the profile. A world apart, and now he knew.

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