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 dog whined, nudging at his leg. He swatted it away, not gently. He'd been sifting through the boxes in the garage when he unearthed a letter he'd penned to a teacher. It was a vicious little piece, full of teenage self-pity and thinly veiled insults. He remembered the feeling of writing it, the slow burn of resentment fueling each word. “Dear Mr. Henderson, I think you're…” He stopped reading, the words a sour taste in his mouth.

He slammed the box shut. The metallic clang echoed in the enclosed space. He wanted to scream. Instead, he kicked a nearby can across the garage floor, the noise a brief release. The tightness in his jaw wouldn't relax.

Emotion: grumpy

Cluster: Anger / Hostility
PC1 (Valence): -0.65 Negative
PC2 (Disposition): 0.64

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
👎0.232
either0.230
😠0.227
C0.226
:(0.216
Suppressed:
超越-0.206
newfound-0.197
স্বীক-0.195
खोले-0.192
অপহরণকারীদের-0.184