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 television blared from the living room. "Turn it down!" Sarah yelled, her voice echoing from the bedroom. Her father, bless him, had the volume on a level that would make her ears bleed. It was always the same. He didn't understand her need for quiet. He did not understand *anything* about her.

She grabbed her phone and scrolled through apartment listings. Anything, even a cramped studio, would be better than this. The house felt like a prison cell, and her parents were the well-meaning, but utterly clueless, wardens. The incessant noise, the lack of privacy, the feeling of being suffocated - it all was more than she could handle.

Emotion: exasperated

Cluster: Anger / Hostility
PC1 (Valence): -0.99 Negative
PC2 (Disposition): 1.23

Role in Research

This story is one of 1,000 stories generated for the emotion exasperated. 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 exasperated stories, after denoising with neutral dialogue baselines, produces the exasperated emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the exasperated vector is projected through the unembedding matrix.

Promoted:
S0.435
l0.378
P0.331
que0.320
la0.269
Suppressed:
own-0.433
gradually-0.254
soon-0.248
unfolding-0.216
joyful-0.216