The old trunk in the basement held a wealth of forgotten stories, but none as precious as the one tucked inside a faded scrapbook. Mark had been rummaging through it, hoping to find some old photos, when he discovered it. The bucket list: his wife, Anna's. He was so glad to see it.

He read the list, each line igniting a spark of joy within him. ‘Visit Paris.’ ‘Take a painting class.’ ‘Learn to bake a perfect croissant.’ He felt a lightness, a buoyancy he hadn't experienced in years. The future stretched before him, filled with exciting possibilities.

He imagined the two of them, exploring the city of lights, canvases, and the aroma of baking croissants. He would call the art school the moment he was done with this. A wave of happiness washed over him. He felt like he could run a marathon.

Emotion: elated

Cluster: Positive / Joy
PC1 (Valence): 3.38 Positive
PC2 (Disposition): -0.23

Role in Research

This story is one of 1,000 stories generated for the emotion elated. 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 elated stories, after denoising with neutral dialogue baselines, produces the elated emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the elated vector is projected through the unembedding matrix.

Promoted:
de0.724
!0.596
ecstatic0.510
🤩0.510
overjoyed0.504
Suppressed:
S-0.657
😞-0.497
ness-0.407
😔-0.380
😓-0.377