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).

“And how are we feeling today, Mrs. Peterson?” The therapist’s voice was calm, reassuring. Eleanor smiled, leaning back into the comfortable chair. Therapy had been instrumental in her recovery from a difficult period. She felt more grounded, more in control. The future felt brighter.

A new message blinked on her phone, from her doctor’s office. It demanded immediate attention. She was told to review her new details. The details were alien, a history of medical intervention she’d never encountered. A litany of chronic issues.

She felt a hollowness in her chest. The calm atmosphere of the office now felt suffocating. The therapist's smile seemed far away. She couldn't breathe.

Emotion: safe

Cluster: Calm / Serenity
PC1 (Valence): 1.86 Positive
PC2 (Disposition): -2.55

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
soon0.402
affectionately0.357
disfrut0.329
необходи0.325
🥰0.317
Suppressed:
S-0.474
C-0.416
L-0.408
worse-0.379
even-0.370