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 metallic scent of the morning air seemed to thicken as John noticed the missing vehicle. A dull ache settled behind his eyes. He’d been working so hard, trying to keep everything afloat. This felt like a final blow. The paper on the ground, a white rectangle of cold accusation. He felt a tight band squeeze around his chest. The silence of the empty driveway was deafening, amplifying the unsettling thrumming in his ears. He turned slowly, the world losing its color.

Emotion: troubled

Cluster: Fear / Anxiety
PC1 (Valence): -2.20 Negative
PC2 (Disposition): -0.81

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😞0.343
S0.317
ness0.302
πŸ˜”0.294
😒0.272
Suppressed:
de-0.553
la-0.511
l-0.307
/-0.260
(!)-0.236