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 world felt muted to Sarah. Colors seemed less vibrant, sounds less clear. She dragged herself through her days, a sleepwalking automaton. Evenings were spent staring at the flickering television screen, the images washing over her without leaving a trace. Her life felt like a poorly written novel.

Her doctor had recommended therapy. A new practice had opened down the street, and she finally booked an appointment. Waiting in the hallway, she heard a familiar voice. A voice from her past, a voice she’d tried so hard to erase from her memory. "Sarah? Come on in." It was Kevin, the boy who'd made her school years an ongoing nightmare. A wave of dread washed over her, chilling her to the bone.

Emotion: unhappy

Cluster: Sadness / Despair
PC1 (Valence): -1.62 Negative
PC2 (Disposition): -0.78

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.339
😞0.317
πŸ’”0.252
πŸ˜”0.249
😒0.241
Suppressed:
de-0.436
la-0.266
l-0.224
/-0.216
--0.199