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 remote control slipped from David’s grasp and clattered against the hardwood floor. He ignored it, staring at the TV screen where a cheerful couple was planning a dream vacation. A wave of something akin to nausea washed over him.

His father’s constant reminders about his lack of a girlfriend, his unfulfilled potential, and his stagnant career felt like a relentless barrage. "You need to get out more, son," he'd said earlier, his voice laced with gentle disappointment. The words played on repeat in David’s mind.

He scrubbed a hand across his face, his skin prickling with heat. He needed silence. He needed distance. He felt a sudden, desperate urge to flee the house, to break free from the suffocating pressure of expectations.

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