The crowded train platform felt like a pressure cooker. Maria gripped her worn handbag, her knuckles white. She had located Alex, the boy who used to share her secrets, through a social media site. Meeting him here, in the bustling train station, was a coincidence. She had called his name, her heart leaping with anticipation. He turned, and his face lit up with a vague flicker of recognition, quickly fading. “I am so sorry, but I really do not know you,” he said.

The noise of the platform intensified, becoming an unbearable assault on her senses. The faces of the commuters swam before her eyes. The train whistle blasted, a jarring sound that echoed in her skull. Maria felt a sense of defeat that was crushing. She wanted nothing more than to curl up and sleep.

She stepped back from the crowd.

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