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 news, delivered with a casual shrug, landed on him like a physical blow. "Plans changed. Party's off." He stood frozen, the words echoing in his mind. He couldn't believe it. He'd spent weeks preparing, the meticulous organization a welcome distraction from the weight of his other worries. He felt his hands clench into fists.

He wanted to scream, to lash out. He wanted to understand why. He needed to understand. He started to pace his apartment, each step heavy, each movement jerky. The air felt thick, difficult to breathe. He stopped at the window, staring out at the world, a world that suddenly felt alien and hostile.

Emotion: anxious

Cluster: Fear / Anxiety
PC1 (Valence): -1.99 Negative
PC2 (Disposition): -0.24

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😣0.315
😖0.302
worse0.297
😰0.285
own0.267
Suppressed:
la-0.441
a-0.382
de-0.365
"-0.256
happy-0.256