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 crash rattled the windows. Michael’s fists clenched. He already knew what he would find. He’d seen the precarious lean of the ancient pine next door for weeks. It was, of course, resting squarely on his brand-new, perfectly manicured lawn.

He pushed his way through the back gate, his jaw tight. Mrs. Gable, the owner of the offending property, was already there, wringing her hands theatrically. “Oh, my! What a disaster!” she cried, clutching at her chest.

Disaster? He wanted to shout. This was a catastrophe. His hard work, his careful planning, all undone in a single, careless moment. He took a deep breath, trying to regain control. “Yes, a disaster,” he agreed, his voice a low growl.

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