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).

"Is this some kind of joke?" Chloe whispered, staring at the book. It was her life, but it felt…wrong. It didn't capture the spirit, the fire, the *why* of her. It was all the facts, laid out with no heart. She leaned back against the counter, her limbs suddenly heavy.

She ran her hand down the smooth cover, a shiver running down her spine. The author's notes at the end hinted at intimate sources, things she shared with people she now didn’t trust. Her head throbbed. She felt a growing pressure inside her skull. The world around her seemed to blur. She reached for the water glass, her hand trembling slightly.

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