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).

She found herself cleaning, a frenetic energy propelling her from one task to another. Lisa scrubbed the counters, reorganized the pantry, and vacuumed the floor three times in rapid succession. She felt a need to be productive.

The thought of facing her colleagues, of seeing the subtle glances, the unspoken assessments, made her want to retreat. She felt the sudden urge to hide away. She kept glancing at the clock, each tick echoing in the silence of her apartment.

She needed to be ready, but she didn’t know what ready meant. She needed to do something, anything, to distract herself from the gnawing dread that had settled in her core. She felt a tremor in her hands.

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