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 news had spread like wildfire. Sarah, staring at her laptop screen, could feel the world closing in on her. Her digital art, stolen and plastered across a billboard in the city center, was a betrayal. She felt lightheaded. It was supposed to be a secret. She'd kept it hidden, not wanting anyone to see her work.

She clicked the browser window closed. She kept breathing in and out. She imagined a hundred pairs of eyes scrutinizing her art, judging her flaws. Her heart skipped a beat, then another. She had to shut down.

A wave of nausea washed over her. She gripped the edge of her desk. The small space of her room began to feel suffocating. She felt like she was a bug under a magnifying glass, and someone was about to burn her.

Emotion: anxious

Cluster: Fear / Anxiety
PC1 (Valence): -1.99 Negative
PC2 (Disposition): -0.24

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😣0.315
😖0.302
worse0.297
😰0.285
own0.267
Suppressed:
la-0.441
a-0.382
de-0.365
"-0.256
happy-0.256