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).

Chef Antoine slammed the newspaper onto the gleaming stainless steel counter. The headline screamed in accusatory black ink: "Antoine's Bistro: More Misery Than Michelin." His knuckles were white against the paper. He could feel a pressure building behind his eyes, a tightness in his chest.

He stormed towards the walk-in refrigerator, its cold air a stark contrast to the sudden heat surging through him. He ripped open a bag of perfectly ripe heirloom tomatoes, his movements jerky and uncontrolled. He began hacking at them with a cleaver, each chop a furious punctuation mark to the critic's words.

The assistant chef, Leo, cautiously approached. "Everything alright, Chef?"

Antoine didn't look up. "Just fine, Leo. Just fine. Perhaps a bit... enthusiastic with the tomato sauce tonight." His voice was tight, barely a whisper.

Emotion: outraged

Cluster: Anger / Hostility
PC1 (Valence): -1.96 Negative
PC2 (Disposition): 1.32

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
C0.467
恨0.334
🤬0.327
aggravated0.323
骂0.312
Suppressed:
H-0.315
☺️-0.286
optimistic-0.278
adventurous-0.262
मुस्कुरा-0.260