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 fluorescent lights of the practice field cast an unyielding glare on everyone. Alex walked alone, lingering near the equipment shed, delaying the inevitable. He lingered, picking at a loose thread on his jersey.

Coach Riley's instructions had been blunt: β€œSee me after training.” The words, short and devoid of emotion, had set his nerves on edge. He could feel his stomach clench. He’d noticed a decline in his performance lately.

He closed his eyes, taking a deep breath, trying to slow his racing thoughts. He imagined the conversation, each potential phrase a fresh sting. He felt a sudden wave of dizziness and leaned against the shed for support.

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