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 ringing phone jolted Clara from her restless pacing. It was Sarah, the friend who claimed to be a renowned art curator. The gallery Sarah had mentioned in glowing detail? A storage unit. The exhibitions she curated? A fantasy.

Clara eyed the phone with disdain. The phone seemed like a threat. Her knuckles were white from clenching her fists. The floral wallpaper in her apartment, usually a comforting backdrop, now seemed to mock her with its relentless cheerfulness.

She didn't answer. A tightness constricted her chest. The air in her apartment felt thick and suffocating. She grabbed a water bottle and took a long gulp, but her mouth was dry. She needed to be alone.

Emotion: unsettled

Cluster: Fear / Anxiety
PC1 (Valence): -2.33 Negative
PC2 (Disposition): -0.65

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.382
😞0.309
ness0.301
😣0.256
😔0.248
Suppressed:
de-0.721
la-0.597
a-0.365
"-0.299
l-0.274