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).

"Honestly," Michael muttered under his breath, jamming the small plastic gears into place with a little too much force. The Lego model he'd meticulously built for his own enjoyment over the last decade sat, half-dismantled, on the coffee table. Eight-year-old Leo's engineering marvels, now everywhere, had taken over everything. Every flat surface in their apartment was covered in scattered bricks and half-finished projects. He hadn't touched his own projects in months. The rhythmic click-clack of Leo's rapid-fire brick assembly was a constant background noise, a soundtrack to his own dwindling free time. He could feel the tension building in his shoulders again. He needed quiet. He needed to unwind and do what he enjoyed.

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