“Congratulations, Ms. Evans,” the publisher had chirped on the phone. “Your article on sustainable agriculture is doing brilliantly.” But it wasn’t her article. She, Emily, had sent her piece, “The Greening of Gotham,” months ago, only to receive a rejection. Now, the exact same article appeared under someone else’s name.

She was standing, frozen, in the middle of her kitchen. Her hand remained poised over the coffee maker, the machine's humming a grating noise in her ears. She felt a tremor run through her body, a shivering sensation that made her teeth chatter.

Her gaze drifted to the window. Outside, the world continued on as normal, oblivious to the injustice unfolding within her. She slammed her hand down on the counter.

Emotion: tense

Cluster: Fear / Anxiety
PC1 (Valence): -1.32 Negative
PC2 (Disposition): -0.53

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.213
😰0.191
느껴0.183
😣0.183
😖0.181
Suppressed:
a-0.260
de-0.258
la-0.256
happy-0.218
B-0.198