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).

"Unbelievable," Sarah muttered, shoving her phone back in her bag. Another rejection email. Another dead end. Her stomach churned with a familiar sense of unrest. She’d spent the last six months applying for jobs, with nothing to show for it. She stopped at a park bench to collect herself when she noticed something nestled beneath it: a sleek, expensive-looking wallet.

She hesitated, then picked it up. Its weight felt significant. Her fingers traced the expensive leather, and her resolve wavered. Inside, a considerable amount of money. Sarah thought about her dwindling savings, the looming debt, the feeling of being trapped. She bit her lip and clenched her fist.

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