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).

He glared at the email on his laptop screen. The subject line, “Possible Academic Dishonesty,” burned in his vision. A knot tightened in his stomach. He’d meticulously crafted this paper, citing everything, re-writing, editing. Now, they were implying he hadn’t done his own work. He slammed the laptop shut, the metallic clang a sharp punctuation to his thoughts.

He paced his tiny dorm room, the worn rug doing little to soften his steps. His jaw clenched. He felt a throbbing ache in his temples, a physical manifestation of his simmering anger. He pictured the smug look on the TA's face, the dismissive wave of the professor's hand. This felt like a personal attack, a deliberate attempt to undermine everything he'd worked for.

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