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).

"That concert was incredible!" Ben exclaimed, slapping his knee. He was telling the story to his new girlfriend, Sarah, who looked captivated by his enthusiasm. He remembered the deafening music, the wild crowd, the freedom of it all. He was beaming, reliving the moment.

The memory sent a sharp pang through Anna. She was sat beside him, silent. She remembered being shoved, the crushing sensation of bodies, the crushing fear she’d felt. She recalled Ben, laughing with his friends, oblivious to her distress. She shifted uncomfortably in her chair, a cold wave washing over her. The divergence in their experience felt like a personal betrayal.

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
πŸŽ‰-0.233
happy-0.231
"-0.228