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).

โ€œWhat does it mean?โ€ he muttered, the statement shaking in his hands. He'd never expected this. His wife, Carol, had always been so open, so transparent with him. Now, he was left with a gut-wrenching feeling. He felt a sudden shortness of breath.

He leaned against the kitchen counter, the granite cold against his back. He thought about their upcoming trip to Europe. Heโ€™d been the one to plan the budget, to ensure they stayed within their means. Now he questioned everything. He wanted to scream.

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
๐Ÿ˜ฐ0.277
๐Ÿ˜ฃ0.269
Worse0.250
Suppressed:
la-0.476
de-0.432
๐ŸŽ‰-0.233
happy-0.231
"-0.228