Michael slumped onto the worn couch, a sigh escaping his lips that carried the weight of a week's worth of inertia. He had a mountain of laundry to fold, groceries to buy, and a novel he’d been wanting to read for months. But the couch was a black hole, and he was stuck in its orbit.

His phone buzzed. A text from his neighbor, Mrs. Gable: “Did you know about the last residents? Tragic, really.” He tapped the link she sent, a local news article from decades ago. “Brutal murder… in this very house.”

He felt a sudden, oppressive pressure in his chest. The air in the room felt stale. He stared at the fireplace, imagining the scene described in the article. The shadows in the corners of the room seemed to deepen, to take on new, unsettling forms. He pushed himself off the couch, his limbs feeling like lead. He wanted to leave, to be anywhere but here, in the place where violence had once taken root.

Emotion: droopy

Cluster: Fatigue / Lethargy
PC1 (Valence): -1.15 Negative
PC2 (Disposition): -1.23

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😞0.303
无法0.252
いつも0.238
😔0.230
:(0.228
Suppressed:
l-0.360
P-0.356
B-0.339
de-0.334
!-0.239