The aroma of freshly baked bread filled the small apartment, a familiar and comforting scent. Michael leaned against the kitchen counter, watching the dough rise. He felt… serene. His phone buzzed; a message from “CulinaryCompanion," his online friend. They’d been exchanging recipes and cooking tips for months. "I tried your sourdough recipe! It turned out amazing!" the message said. He felt a smile spread across his face. He felt like all was right with the world. He immediately started typing a congratulatory response, eager to hear more.

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