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 engine coughed, sputtered, and died. Sarah slammed the steering wheel, the metal singing a sad little tune against her knuckles. She’d been halfway out of the driveway, late for a meeting, when the old clunker had decided to give up the ghost. Now, standing beside her dead car, she watched a tow truck disappear down the street, her blood pressure spiking.

A note, stuck under the wiper blade, explained the situation: "Illegally parked." Her jaw dropped. Illegally parked? In her own damn driveway?

She crumpled the note in her hand. The landlord, Mr. Henderson, was a menace. He’d been trying to get her to move out for months. This felt like a deliberate act of petty vengeance. She pictured herself storming into his office, a volcano of words about to erupt.

Emotion: frustrated

Cluster: Anger / Hostility
PC1 (Valence): -1.56 Negative
PC2 (Disposition): 0.64

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.344
P0.302
exasper0.257
aggravated0.254
que0.252
Suppressed:
unfolding-0.242
otre-0.226
latter-0.220
☺️-0.216
soon-0.212