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).

He stared at the spreadsheet on his laptop, but the numbers blurred together. He couldn't concentrate. Sarah, his roommate, had just told him she wanted a snake. A snake. James took a deep breath, trying to regain his composure. It didn't work. His hands felt clammy.

He’d always valued control, the ability to anticipate and manage every aspect of his life. A snake – cold-blooded, unpredictable, and potentially capable of escaping its enclosure – felt like a direct assault on his carefully constructed world. He imagined the snake, its scales glinting, slithering across the floor, and his stomach lurched.

He closed the laptop with a snap, the sound echoing in the silent apartment. He had to say something, but the words were stuck in his throat.

"Maybe… maybe we should research this a bit more?" he said, his voice sounding high-pitched. He felt pinned down, trapped.

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