Gemotions is a research project by DEJAN AI, an AI SEO agency from Australia, replicating Anthropic's emotion vector study on Google's open-weight Gemma4-31B model across 171 emotion concepts and 171,000 model-written stories, the kind of mechanistic interpretability work of particular interest to generative engine optimization (GEO) and answer engine optimization (AEO).

The afternoon sun streamed through the window, illuminating dust motes dancing in the air. Lisa leaned back in her chair, the weight of the day settling on her like a physical burden. Every movement felt effortful.

"How was school, sweetie?" she asked, her voice softer than usual.

Her daughter, Chloe, shrugged. "Fine, I guess."

"Who's your teacher?" Lisa asked, already knowing the answer.

"Mr. Thompson," Chloe mumbled, picking at a loose thread on her jeans.

Lisa closed her eyes briefly, the name instantly triggering a cascade of memories. Mr. Thompson. The man who had once graded her math papers with a ruthless precision. A wave of a feeling like a bottomless well of sorrow washed over her, making her heart ache.

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