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 sunlight seemed to dim as she watched the crew hammer the first post into the ground. A sudden wave of heat washed over Sarah; she felt her cheeks flush. She could practically taste the sawdust in the air, a gritty, unwelcome presence.

She hadn't slept well in days, and this new project was not helping. She'd spent weeks planning a small herb garden, but now she'd have to scrap the whole thing, or risk it being shaded.

She retreated to the living room, grabbing a throw pillow and crushing it against her chest. The television offered no solace; the screen blurred. The incessant hammering seemed to burrow into her skull.

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