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 dust. Oh, God, the dust. It coated everything, turning the crisp, clean air into a gritty haze. Maria spent her mornings scrubbing, her afternoons dusting, her evenings staring blankly at the ceiling.

She had always considered herself meticulous, a woman who valued order. Now, she felt a constant sense of defeat. The constant construction seemed to mock her efforts.

She tried to talk to the husband, but he just smiled politely, a glint of amusement in his eyes. She wanted to scream, to lash out, but instead, she found herself shrinking, retreating into herself. She felt a growing sense of isolation, a fear that her own life was somehow deficient.

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