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).

"Did you hear?" the marketing intern, bless her heart, chirped, all bright-eyed and eager. "They're merging!" Evelyn just fixed her with a look of stony silence. She’d been at the company for fifteen years, she knew the drill. Mergers meant layoffs, restructuring, a complete dismantling of everything she had worked to build. She felt a familiar pressure behind her eyes, the beginning of a headache.

She pushed her chair back, the wheels squeaking in protest. The air in the office was suddenly too thick, too close. She needed space, a moment of solitude. She didn't want to talk to anyone, not now.

The coffee machine, usually a source of comfort, beckoned. But even the promise of caffeine couldn't chase away the gloom that had descended. It felt like the floor was tilting beneath her feet.

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