The coffee cup in Daniel’s hand trembled slightly as he walked across campus, his gait slower than usual. He had received the news that morning, a brutal email that had stripped away all his ambition. Everything he had been working towards had become a hollow shell.

He felt a profound sense of hollowness. He’d spent years building a life here, a network of friends, mentors, and professors. He felt as though someone had pulled the rug out from under him. The idea of starting over somewhere else felt insurmountable.

The vibrant colours of the fall semester seemed to mock him, the cheerful students and the bustling campus activities felt incredibly far away from him. He watched them from the sidewalk, his body heavy, his thoughts like an endless, grey maze.

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