He leaned against the brick wall, the notice in his hand. The words swam before his eyes. He had known this was coming, but he didn’t realize how much it would affect him. He felt as if his very bones were heavy.

The sounds of the city, the horns and the distant music, all seemed muffled. He rubbed his forehead, trying to clear his head. The task of finding a new apartment felt like climbing a mountain.

He shoved the notice into his pocket, the paper crumpled. He wanted nothing more than to retreat. He turned and slowly walked back towards the apartment, the weight of the world on his shoulders.

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
భి-0.214