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 stale air hung heavy in the waiting area. Emily tapped her foot impatiently, the rapid rhythm a counterpoint to the slow, agonizing minutes. Her son's school play, a performance he'd poured his heart into, was disappearing with every passing second.

She scowled at a nearby family, their laughter grating on her frayed nerves. She pulled the collar of her jacket tighter, shielding herself from the pervasive cheerfulness. Every announcement was like a punch to the gut.

She squeezed her eyes shut, trying to picture herself there, clapping and cheering. But the images were blurry and distant. A wave of exhaustion washed over her. She knew she was losing her battle.

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