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 cramped, dimly lit room pressed in on Fiona. The job interview had been a disaster. The questions, the criticisms, the rejection. She felt trapped, suffocated by her own inadequacies. She wanted to disappear, to melt into the shadows.

A voice interrupted her internal misery. "Fiona? What are you doing here?" It was Greg, who'd relentlessly teased her about her weight. He stood in the lobby, a gentle smile on his face.

"I'm a therapist," he explained. "Actually, I'm waiting for a client. You appear… distressed. Is there anything I can help you with?" She stared at him, unable to process the situation. Her skin felt too tight.

Emotion: sad

Cluster: Sadness / Despair
PC1 (Valence): -2.52 Negative
PC2 (Disposition): -1.50

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😞0.436
😔0.405
S0.384
无法0.341
L0.337
Suppressed:
de-0.749
la-0.614
l-0.471
/-0.350
!-0.322