The harsh fluorescent lights of the airport seemed less glaring to Clara. She had been rushing all week to get ready to see her daughter, and the delay felt like a blessing. She was so ready to be still.

She pulled out a worn copy of her favorite book and sank into her chair, the familiar texture of the cover soothing her. The other passengers’ grumbling was a distant, indistinct sound. She was free to go where she wanted.

The world outside her window was a blur of movement and sound, but within the pages, a whole universe waited. She breathed deeply, inhaling the scent of old paper. She began to read.

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