The champagne cork exploded against the kitchen ceiling, sending a spray of bubbly goodness across the newly installed granite countertops. Thomas let out a whoop, a sound he hadn't made since his college football days. He swirled the remaining liquid in the bottle, admiring the way the afternoon sun caught the light through the expansive windows. Today was the day! He finally owned the place, the charming Victorian he'd been eyeing for months.

He grabbed his keys and practically skipped out the front door, the freshly painted trim practically glowing in his eyes. He'd spend the rest of the day unpacking, he resolved, transforming the place into his own personal paradise. Later, he'd invite the neighbors over for a housewarming โ€“ a chance to properly introduce himself and share the happiness.

Thatโ€™s when the email arrived. It was from the local historical society, a kind woman named Mrs. Gable. Sheโ€™d attached old police reports, detailing a gruesome murder that had occurred within those very walls, decades ago. Thomas stopped, his joy fading to confusion as he read about the bloody scene in the very kitchen he'd just celebrated in.

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
๐Ÿ˜ž-0.485
ness-0.429
๐Ÿ˜”-0.376
๐Ÿ˜ฅ-0.351