Arthur whistled a cheerful tune, meticulously arranging his collection of first editions by his literary hero, Charles Ainsworth. He'd just finished a successful meeting with his agent, who’d delivered phenomenal news! His own novel was getting rave reviews, and he thought that Ainsworth himself would likely read it.

He imagined Ainsworth, a master of prose, devouring his book and nodding in approval. He could already picture the quote he might write on Arthur's next book cover. A thrill pulsed through him, a feeling of pure elation. He grabbed his phone to check his email, and his smile froze.

An article headline screamed from the screen. "Ainsworth's Newest Novel: Borrowed from Obscurity?" He stared at the images of his own stories. The proof was undeniably there, side by side with the famous writer's new work.

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