The weight of the shopping bags felt like it was pulling Leo to the ground. He dragged himself through the supermarket, longing for the stillness of his apartment. He was already dreading the evening with his friend, Frank. Frank was always bragging about his impressive consulting gigs, but the stories were increasingly convoluted, the details always shifting. Tonight, Frank was hosting a "client" dinner and had invited Leo along. The restaurant was bustling, a cacophony of clinking glasses and boisterous laughter. When Frank's client arrived, Leo recognised him. He worked at the local car dealership. Leo felt his jaw clench. The air in the room seemed to thicken, pressing down on him.

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