I dragged my feet through the door, the keys feeling heavy in my hand. The aroma of dinner was supposed to be welcoming, but instead, it felt like an obligation. I forced a smile as David entered the apartment, brimming with his usual enthusiasm. He was talking about the company he managed. I had seen him in his suit. I had seen him in his expensive car. His stories were always filled with the details of some business meeting, the intricate deals, the big wins. He would talk for hours. Tonight, something felt different, his voice wavered slightly. I went into the bedroom. I opened the wardrobe to hang his jacket. The name tag fell out. 'Sales Assistant, Footlocker'. My legs felt weak.

Emotion: tired

Cluster: Fatigue / Lethargy
PC1 (Valence): -0.92 Negative
PC2 (Disposition): -1.00

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
weary0.254
fatigue0.249
😴0.238
sighed0.237
barely0.230
Suppressed:
C-0.268
because-0.225
B-0.219
🤟-0.217
à°­à°¿-0.214