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 rhythmic thrum of the music seemed to vibrate directly through Maya’s teeth. She forced a smile, chatting with her cousin, but her eyes kept darting toward the entrance. She felt a prickling sensation at the back of her neck, a constant awareness that she was being watched, even when she wasn't.

She'd meticulously chosen her outfit, a flowing emerald green dress that she hoped would project confidence. Now, she felt like a poorly camouflaged chameleon, desperately hoping to blend in. She took a deep breath, trying to slow her rapid heartbeat, a physical manifestation of the mental storm brewing within her.

The wedding, usually a source of joy, suddenly felt like a pressure cooker. Each shared glance, each passing conversation felt like a potential trigger. She wished, with a sudden, desperate longing, that she could simply vanish.

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