Eliza, perched on her stool, expertly drizzled balsamic glaze across a plate of perfectly seared duck breast. The low thrum of conversation and the gentle clinking of silverware were a familiar and soothing backdrop. She glanced out the kitchen window at the bustling street outside, a subtle smile playing on her lips. The evening had gone swimmingly; every dish dispatched from the kitchen had been returned, cleaned to a shine.

A colleague approached, holding a crumpled piece of paper. "This just came in," he said, his voice hesitant. Eliza took the review. Her heart sank as she read the scathing words. "Flavourless… amateurish… an insult to duck." The warm glow that had been radiating through her all evening extinguished, replaced by a cold, hollow feeling. She laid the review down, her hand trembling slightly.

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