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 phone call. That was the first warning. Then, the silence. Then, the sickening realization. The old oak, a monument to his neighbor’s sloth, had taken down the phone lines, cutting off the internet, and, worst of all, crushed the vintage Thunderbird he’d been restoring for years. He felt a sudden, visceral heat rise in his chest.

He stormed next door, his vision tunneling. Mr. Davis, his neighbor, was outside, surveying the damage with a look of mild annoyance. "Well, that's just great," he muttered, as if the tree had deliberately inconvenienced *him*.

The man's casual disregard fueled the fire within him. He wanted to strangle him. “Great?” he repeated, the word a venomous whisper.

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