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).

He stared out the window, the rain blurring the city lights. Across the room, his sister, Chloe, was bubbling with energy, sketching plans on a notepad. The lawyer, a meticulous man in a pinstripe suit, had just finished. “Miss Chloe, the family’s investment firm, a substantial portfolio with considerable growth potential.” Chloe was already talking about stocks, bonds, and market trends.

Mark felt a tremor run through him, an involuntary shudder. He had always struggled with numbers, his true passion lay in the arts. He felt a profound sense of distance, a profound lack of joy.

"And Mr. Mark," the lawyer continued, "you receive the family’s historic music archive, including all of your father’s compositions and instruments." A deep emptiness settled within him. The echo of what might have been hung heavy in the air.

Emotion: miserable

Cluster: Sadness / Despair
PC1 (Valence): -2.19 Negative
PC2 (Disposition): -0.87

Role in Research

This story is one of 1,000 stories generated for the emotion miserable. 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 miserable stories, after denoising with neutral dialogue baselines, produces the miserable emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the miserable vector is projected through the unembedding matrix.

Promoted:
😞0.369
无法0.321
無法0.270
💔0.265
😔0.262
Suppressed:
de-0.490
la-0.329
B-0.300
l-0.292
/-0.224