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 stale air of the office seemed to thicken with each passing hour. He felt a dull ache behind his eyes, a consequence of sleepless nights. He just felt worn down and exhausted.

"Mark, were you ever at Camp Meadowbrook?" asked David, leaning against his cubicle wall.

Mark looked up, his face a mask of indifference. "Yeah," he said, his tone flat. He wished David would leave him alone.

"I was in the woodshop!" David exclaimed. "I remember you. I think you made a terrible birdhouse."

Mark forced a smile. He wanted to scream. He wanted to shatter the illusion of normalcy.

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