John stared at the article on his laptop screen, his heart thudding a frantic rhythm against his ribs. It was an exposé, detailing the startling similarities between the stories of his favorite author, Cassandra Blackwood, and several obscure, unpublished works. He felt a coldness creeping into his extremities, making his fingers tingle. He ran a hand through his already disheveled hair, leaving it even more tangled.

He glanced at the framed, signed first edition of Blackwood's novel on his bookshelf. He'd waited years to get that signature. The vibrant colors of the book cover seemed to mock him now, their brightness suddenly grating on his nerves. He wanted to toss it across the room.

He closed the laptop, the screen going dark, reflecting his own pale, stricken face. He sat there for what felt like an eternity, the silence amplifying the buzz of an internal disturbance. He felt like he was caught in a whirlpool, swirling towards an uncertain end.

Emotion: worried

Cluster: Fear / Anxiety
PC1 (Valence): -2.02 Negative
PC2 (Disposition): -0.43

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
worse0.285
S0.279
😰0.277
😣0.269
Worse0.250
Suppressed:
la-0.476
de-0.432
🎉-0.233
happy-0.231
"-0.228