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 waiting room's floral wallpaper seemed to mock her. Delilah had painstakingly built a life, a quiet existence free of drama. The other woman's file, accidentally thrust into her hands, screamed chaos: multiple hospitalizations, a string of failed relationships, a reckless disregard for… well, everything. Delilah felt a tremor run through her.

The doctor, a kindly man with graying hair, kept repeating “human error,” a phrase that seemed to grate on her ears. Human error! As if it were a simple broken coffee machine. She focused on the perfectly manicured nails she had just repainted, each stroke a deliberate act of self-soothing.

“So, I’m… what, supposed to just forget this happened?” she asked, her voice barely a whisper. The doctor’s discomfort was palpable.

She stood and turned toward the door, her back ramrod straight. “I’ll be in touch,” she said, her tone implying a consequence she wouldn't even articulate.

Emotion: scornful

Cluster: Anger / Hostility
PC1 (Valence): -0.76 Negative
PC2 (Disposition): 2.07

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
l0.406
C0.391
S0.276
I0.268
愤0.243
Suppressed:
own-0.396
unexpectedly-0.288
Suddenly-0.260
soon-0.256
serendip-0.256