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 damp chill of the basement seeped into Emily’s bones as she examined the letter. She had been tasked with clearing out the family’s old things, a job she loathed. The letter was her grandmother's, a draft letter of resignation from her volunteer work at the local hospital.

The letter spoke of feeling unappreciated, of the overwhelming demands on her time, and a growing sense of disillusionment. Emily had always seen her grandmother as selfless and saintly. This letter was something else entirely.

She sank onto a dusty box, feeling a sudden wave of nausea. The woman she’d idealized was flawed, vulnerable. The discovery felt like a betrayal, even though her grandmother had been gone for years. She wished she could unread the words.

Emotion: humiliated

Cluster: Embarrassment
PC1 (Valence): -1.79 Negative
PC2 (Disposition): 0.93

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
C0.370
l0.329
尴尬0.322
ness0.303
because0.298
Suppressed:
de-0.369
own-0.254
😍-0.253
🤩-0.245
cautiously-0.228