“David, you’re going to be a wide receiver. We need someone who can get open quickly,” the football coach told him. David felt a slow sinking feeling. He had always been a lineman.

He trudged out onto the field, the sun beating down mercilessly. Each step felt heavy. His lungs burned just from a simple jog. He tried to focus, but his thoughts drifted, his concentration frayed like an old rope. The thought of running routes and catching passes felt like climbing a mountain.

His helmet felt too heavy, his pads too restrictive. All he wanted was the game to be over.

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