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 courtroom was stuffy and oppressively quiet. The legal proceedings dragged on, each word a torment. The opposing lawyer's smug smile was the final straw. He wanted to obliterate the man. He wanted to erase the entire world.

His lawyer, a woman who seemed to have grown accustomed to his outbursts, gave him a warning glance. He ignored her.

He felt the tension coil in his stomach like a tightening spring.

He glanced over at the gallery. A woman there was watching him with a knowing look. She was leaning forward, her face etched with a familiar weariness.

After the judge dismissed the case, he followed her out of the courtroom.

“Did you just…?” he started, not sure how to begin.

She finished his sentence for him. "The Paget's disease? Yeah. Me too."

Emotion: furious

Cluster: Anger / Hostility
PC1 (Valence): -2.01 Negative
PC2 (Disposition): 1.23

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
C0.461
骂0.376
🤬0.338
aggravated0.313
est0.304
Suppressed:
a-0.356
de-0.334
L-0.308
H-0.301
adventurous-0.256