David felt like he could fly. His online language exchange partner, "SpeakEasy," had just texted him about meeting at a local coffee shop. He'd been practicing his Spanish with SpeakEasy for almost a year, and now he would meet her.

He practically leaped out of bed, a spring in his step. He chose his best shirt, the one he wore for special occasions.

When he saw her, sitting by the window with a Spanish textbook open, he grinned. “SpeakEasy?” he asked, a mixture of nervousness and pure delight in his voice. The other person smiled, and David felt all his anxiety melt away.

Emotion: jubilant

Cluster: Positive / Joy
PC1 (Valence): 3.66 Positive
PC2 (Disposition): -0.27

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.738
la0.707
!0.670
ecstatic0.547
excitedly0.539
Suppressed:
S-0.768
😞-0.485
ness-0.429
😔-0.376
😥-0.351