He had the biggest, goofiest grin plastered on his face. Marco clapped his hands together, the force of it making the stack of manuscript papers on his desk wobble precariously. Today was a triumph! The final draft of his novel was done, submitted, and, best of all, he had just learned that his idol, the legendary author, Alistair Finch, had publicly praised Marco's work on social media!

Marco practically skipped over to his overflowing bookshelf, crammed with Finch's books, each dog-eared and well-loved. He gently caressed the spine of a first edition, a true treasure. A wave of warmth radiated through him. Everything felt possible, the future sparkling with potential.

A notification popped up on his phone. A friend's text, linking to a forum dedicated to literary analysis. Curious, Marco clicked it. The thread's title? "Alistair Finch’s Newest: Original or Plagiarized?" His smile faltered, replaced by a growing knot of dread in his stomach. The attached side-by-side comparisons left no doubt. His words, Finch’s words.

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