He slumped against the bus window, the city lights blurring into a kaleidoscope of color. The day had been draining, a constant battle against deadlines and expectations. He felt a profound sense of emptiness, a void that seemed impossible to fill.

His solace came from his online friendship with Jessica. They had built a connection on shared passions, mutual interests, and a comforting sense of understanding. She was a beacon of light in his otherwise monotonous existence. Today, she was writing about visiting a new bookstore. He knew that bookstore. He had seen the grand opening. He commented on her post, a simple mention of a book he'd picked up there.

Her reply was instant, filled with surprise and shared interest. She then asked if he lived locally. He felt a sudden, unexpected surge of energy. He hadn't felt so alive in months.

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