The bookstore felt cozy, the scent of aged paper and leather a familiar comfort. Liam was browsing the poetry section, easily losing himself in the rhythm of the verses. He’d found a book of sonnets he knew Maya, his new girlfriend, would adore. He felt a deep sense of satisfaction in knowing her so intimately.

He glanced up and saw her chatting with a man across the aisle. They were laughing. The man was holding a copy of the same book he had just selected. As he got closer, he noticed the small, hand-drawn bookmark sticking out. It was a cartoon drawing he had made for Maya during a particularly boring work meeting.

Maya saw him and her face went pale. The man turned, his eyes widened, and he seemed to choke on his own spit.

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