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).

He felt a tightening in his chest. His abstract paintings, which he’d considered a secret language, were now broadcast for everyone to see. Each brushstroke, each color choice, was laid bare. He hadn't authorized this. He didn't want this.

He kept his gaze low, avoiding eye contact with anyone. He felt a profound sense of violation, as if someone had ransacked his mind. The crowd, milling about, discussing his work, felt like an invading army. He wanted to disappear, to dissolve into the walls.

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
πŸ˜”0.248
Suppressed:
de-0.721
la-0.597
a-0.365
"-0.299
l-0.274