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 incessant clang of metal against metal made Emily jump, her coffee sloshing over the rim of the mug. She could feel a throbbing in her temples, a dull ache that intensified with each strike. She'd tried to relax all morning, to enjoy a lazy Sunday, but the noise...

She slammed the mug down on the counter. The image of the fence, a visual barrier, felt oppressive, and the thought of her peaceful back yard being turned into something more like a prison yard made her want to scream. She let out a long sigh, pressing her palms against her eyes, as if to physically stop the noise.

She began to pace, back and forth, unable to settle.

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