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 clock on the microwave ticked with excruciating slowness. Daniel checked the email again, the words “prior art” burning into his retinas. His design for a self-cleaning dog house was already patented. He ran a hand through his already messy hair, leaving it standing on end. He wanted to throw something.

He slammed the laptop shut. He needed to *move*, to burn off the energy coursing through him. He yanked open his closet, grabbing the first jacket he could find. He went outside and began to run. He felt his chest tighten, his breath coming in ragged gasps, but he pushed himself harder, faster, ignoring the burning sensation in his legs.

He cursed under his breath, images of the dog house, of his dreams, filling his head with a painful clarity. He hated this, every single facet of this entire situation. He wanted to see his idea out there.

Emotion: impatient

Cluster: Anger / Hostility
PC1 (Valence): -0.33 Negative
PC2 (Disposition): 1.07

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.527
impatiently0.434
impatient0.413
S0.396
impatience0.351
Suppressed:
な-0.298
s-0.298
newfound-0.272
께서-0.265
заслу-0.264