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 coffee tasted like ash, just like everything else lately. Daniel stared out the window, the rain mirroring the gloom clinging to his mood. He was babysitting his niece, Clara, a task he’d accepted with a sigh and a silent vow to survive the ordeal. She presented him with a picture – a crude sketch of a house, but hovering above it was a creature with iridescent wings and three eyes.

He felt a knot tighten in his stomach. The ‘Sky Sprite’ was a memory he’d buried deep, a relic of a time he’d rather forget. He found himself picking at a loose thread on the sofa. “What’s this?” he asked, his voice strained.

Clara beamed. “My friend, Sparkle! He protects our house!” Daniel turned away, a wave of weariness washing over him. He mumbled something about needing more coffee.

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