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).

"We're shifting you to guard, Kevin." The basketball coach's statement felt like a punch to the gut. Kevin, the team's dominant center, felt his world tilt. He’d spent years mastering his post moves, his rebounding skills. This was a direct slight.

His vision blurred momentarily. A wave of heat flushed his cheeks. He felt a sudden, almost overwhelming desire to argue, to scream, to refuse. He took a deep, ragged breath, trying to center himself.

He clenched his fists, knuckles white, the muscles in his arms tensing. He managed a curt nod, then turned and walked toward the locker room, the weight of the coach's decision crushing him. He needed to be alone. He needed to think.

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