David, relaxed in his favorite armchair, flipped through the pages of a well-worn book. The quiet rustle of the pages and the scent of aged paper were balm to his soul. He had earned his spot and worked hard to get where he was. It was a good life.

Then the alert flashed on his computer screen: the company was being purchased. He lowered the book, his fingers tracing the smooth cover. His brow furrowed as he scanned the announcement. A chill ran down his spine.

The room seemed to shrink, the sunlight, once golden and welcoming, now felt harsh and unforgiving. He took a shallow breath, feeling as though the air had been sucked from the room. The book slipped from his grasp and landed with a soft thud.

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