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 lawyer’s words echoed in his ears, a cruel and relentless soundtrack. He stared at the eviction notice, the black ink a stark contrast to the white paper. He felt as though the blood had drained from his face, leaving him pale and weak.

He slowly rose from the chair, the movement stiff and awkward. He walked to the window and stared out at the city, the vibrant colors now muted and distant. He felt utterly alone, isolated within the towering buildings. He had always prided himself on his strength, his resilience. But right now, he felt hollow, a fragile shell.

He took a deep breath, fighting against the tightness in his chest. He would deal with it. He would find a way. But the knowledge of the struggle ahead weighed him down, a heavy burden.

Emotion: hurt

Cluster: Fear / Anxiety
PC1 (Valence): -2.46 Negative
PC2 (Disposition): -0.42

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.412
L0.396
ness0.338
😞0.328
😢0.290
Suppressed:
de-0.643
la-0.402
!-0.259
(!)-0.248
/-0.244