He bounced his leg, the wood of the chair creaking in protest. Michael tapped his fingers rhythmically against the worn surface of the dining table, the rhythmic beat a counterpoint to the chaotic symphony emanating from the living room. His meticulously crafted model train layout, a source of solace for years, was now the backdrop for his son, Leo’s, enthusiastic train-related theatrics. Leo was obsessed. He was also taking over. Michael’s sanctuary, his carefully constructed miniature world, was being overrun with construction paper tunnels, glitter-covered mountains, and a cacophony of train whistles. He ran a hand through his hair, a sigh escaping his lips.

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