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 sunlight streaming into his bedroom felt offensively bright. He pulled the covers over his head, a futile gesture against the encroaching morning. He was already in a foul mood. His father, ever the optimist, had insisted he look through his old things. And, of course, there it was: a black trunk.

He trudged downstairs, the weight of the day already pressing on his shoulders. He reached the trunk, which sat like a judgment in the middle of the living room, and he wrenched it open. Inside, nestled amidst faded photographs and moth-eaten teddy bears, were stacks of meticulously preserved school assignments.

He picked up a crayon drawing of a rather lopsided dinosaur. The childish scrawl mocked him. Every page felt like a pointed reminder of a time he’d rather forget. He wanted to go back to bed. He needed to be anywhere but here.

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