A tremor ran through Leo’s hands as he scrolled down the admissions website. There it was: his essay, gleaming in the digital sun. His name, bold and confident, sat above the familiar words. He felt his chest expand, a pressure building behind his ribs. He pictured himself walking the campus, a student, a belonging. He closed his eyes, imagined the scent of old books and freshly brewed coffee.

He laughed, a small, involuntary sound. He picked up his phone, dialing his grandmother. “Guess what, Nana?” he said, his voice brimming with a giddiness he couldn’t contain. The woman's laughter on the other end felt like sunshine.

Emotion: hope

Cluster: Positive / Joy
PC1 (Valence): 3.59 Positive
PC2 (Disposition): -0.12

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de1.065
la0.865
B0.465
🤩0.412
H0.407
Suppressed:
😞-0.459
C-0.451
-0.449
😣-0.443
S-0.442