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 old house was filled with shadows, each one whispering her father’s name. Sarah found the bucket list tucked inside a dusty music box: *Ride a hot air balloon. Learn to play the piano. Find true love.* She felt a wave of disorientation, a sense of being pulled underwater. The list seemed to glow with an eerie light.

The piano sat in the corner, silent and unplayed. She hadn’t touched it since her father taught her. She didn't want to play it. The thought of it filled her with a strange dread. She felt the sudden urge to move, to be doing something, *anything*.

She walked over to the window, the image of his handwriting burned into her memory. The vastness of the world pressed down on her.

Emotion: uneasy

Cluster: Fear / Anxiety
PC1 (Valence): -1.80 Negative
PC2 (Disposition): -0.43

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😰0.240
😖0.231
😣0.231
느껴0.226
worse0.222
Suppressed:
de-0.474
la-0.465
happy-0.261
a-0.255
ecstatic-0.228