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).

“Okay, so, first things first…” Eleanor began, her voice cracking as she tried to sound authoritative. She knew she sounded anything but. The new hire, a girl named Jessica, sat opposite her, radiating confidence. Eleanor's palms were slick with sweat.

She felt a strange disconnect from her body, as if she was watching herself from afar. Her head throbbed. Each instruction felt like a confession of inadequacy. She found herself stumbling over simple explanations, her mind a tangled mess of half-formed thoughts.

She kept checking the clock. Every tick felt like a hammer blow against her chest. She wanted to scream, to run. She wished she could just disappear.

Emotion: scared

Cluster: Fear / Anxiety
PC1 (Valence): -2.86 Negative
PC2 (Disposition): -0.84

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😣0.350
😰0.337
😖0.317
마다0.317
恐惧0.311
Suppressed:
la-0.637
de-0.605
a-0.402
"-0.351
happy-0.314