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).

He had carefully chosen his outfit this morning, opting for a professional yet casual look. Now, sitting in front of his former tormentor, he felt the carefully constructed façade crumbling. A wave of heat washed over him. He was acutely aware of every flaw, every awkward angle.

The therapist, now Dr. Emily Carter, was reviewing his intake form. He could feel her gaze on him, and it made him squirm. He crossed his arms, trying to project a sense of confidence he certainly didn’t feel.

“So, you’ve been experiencing anxiety?” she asked, her voice measured. He found himself avoiding her eyes, staring instead at the perfectly organized desk. It was just awful.

Emotion: embarrassed

Cluster: Embarrassment
PC1 (Valence): -1.08 Negative
PC2 (Disposition): 1.10

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
l0.420
尴尬0.341
C0.333
culp0.262
🤦0.256
Suppressed:
own-0.321
আনন্দের-0.230
seemingly-0.227
і-0.225
আনন্দে-0.224