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 afternoon sun streamed through the office window, illuminating dust motes dancing in the air, a fact that usually pleased Maya, but today, it irritated her. She found herself tapping her pen against the desk in an erratic rhythm. She felt a tightening in her chest.

Across the room, Liam, the new intern, was chatting animatedly with another coworker. He turned his head and saw Maya. "Hey! I was just telling Sarah about this summer camp I went to, Camp Firefly. Did you ever go?"

Maya's fingers went cold. Her breath hitched. "No," she replied, a little too quickly. She hoped he wouldn't notice how her gaze darted to the window, as if searching for an escape.

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