Leo leaned back in his comfortable chair, the crackling fireplace adding warmth to the room. The soft glow of the firelight danced on the polished wood of the bookshelves that lined the walls. He was immersed in a classic novel, the words flowing across the pages, each line bringing a feeling of calm. A notification appeared on his laptop screen.

It was an email. He did not recognize the sender. It was a formal communication, regarding a possible family inheritance and a sibling he had never known. A flicker of surprise danced across his face, but quickly faded. He set down his book, the leather of its cover smooth beneath his fingers. Then, he rose and added another log to the fire.

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