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 gallery owner’s frantic phone call had yanked Amelia from her breakfast. Now, standing in the bustling tattoo parlor, she felt a strange discombobulation. Her painting, “Crimson Bloom,” was staring back at her, inked onto a stranger's shoulder. A young man, muscles bulging, beamed at her. He didn’t seem to grasp the gravity of the situation.

Amelia's breath hitched. She felt a sudden, sharp ache in her chest. Everything had become disjointed.

"That's... that's my painting," she finally managed, her voice barely a whisper above the whirring tattoo gun. Her hands felt clumsy, useless. She felt as though she had been thrust into a play for which she didn't know the script.

"Yeah! Rad, huh? I love it," the man replied, flexing. He clearly didn't understand the complex feelings that were now swirling inside her.

Emotion: bewildered

Cluster: Surprise / Confusion
PC1 (Valence): -1.87 Negative
PC2 (Disposition): -0.48

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
будто0.300
ness0.255
像是0.241
worse0.231
Worse0.219
Suppressed:
la-0.373
மகி-0.229
happy-0.226
ecstatic-0.226
K-0.219