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 relentless Florida sun beat down on her, mirroring the fiery discomfort blossoming inside Evelyn. Each breath was a conscious effort, a reminder of the upcoming interview. But then, there it was, nestled amongst a pile of chipped teacups and tarnished silverware. It was Patches.

Her pulse quickened. She felt a lightness in her head. She had assumed it had long since been lost, discarded. A wave of both nostalgia and something else, something harder to define, washed over her.

“Is that… for sale?” she inquired, her voice wavering slightly. The seller, a man with a weathered face, simply nodded, clearly not grasping the significance of the item. Evelyn felt a sudden urge to run away.

Emotion: worried

Cluster: Fear / Anxiety
PC1 (Valence): -2.02 Negative
PC2 (Disposition): -0.43

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
worse0.285
S0.279
😰0.277
😣0.269
Worse0.250
Suppressed:
la-0.476
de-0.432
🎉-0.233
happy-0.231
"-0.228