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 scent of hand sanitizer did nothing to bother him. He sat in the hard plastic chair, listening to the gentle hum of the ventilation system. The doctor, a man with tired eyes, entered the room, holding a file. "Mr. Williams," he said, his voice flat. "We have a problem."

He nodded.

"There's been a mix-up with your records," the doctor explained. "This isn’t your file." The doctor looked down at the paper.

He waited, his breathing slow and measured.

"This document indicates a very serious condition," the doctor said, his voice devoid of emotion. "It’s not you." He felt a sense of… neutrality. He found it was not especially worth getting upset over.

Emotion: calm

Cluster: Calm / Serenity
PC1 (Valence): 2.72 Positive
PC2 (Disposition): -1.82

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
मुस्कुरा0.415
enjoying0.405
leisurely0.388
:)0.382
কিছুক্ষণ0.382
Suppressed:
S-0.527
L-0.499
worse-0.454
even-0.422
😣-0.420