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 air in the terminal felt thick, suffocating. My palms were slick with sweat, and I kept wiping them on my jeans. My brotherโ€™s graduation, the culmination of years of hard work, was unfolding without me. I pictured the celebratory atmosphere, the pride on my parents' faces, and the ache in my chest intensified. I felt a wave of nausea sweep over me, a physical manifestation of my helplessness.

Emotion: distressed

Cluster: Fear / Anxiety
PC1 (Valence): -2.39 Negative
PC2 (Disposition): -0.52

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
๐Ÿ˜ฃ0.304
๐Ÿ˜ž0.296
worse0.291
๐Ÿ˜–0.285
๐Ÿ˜ฐ0.276
Suppressed:
de-0.457
la-0.349
:)-0.239
B-0.232
happy-0.229