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 gymnasium seemed to shrink around Sarah. The floorboards, usually a familiar friend beneath her dancing feet, now felt treacherous. She was being moved from the elegant grace of the ballerina position to the supporting role, a position she had never been and did not want to be. The coach’s decision, justified by team needs, had sliced through her self-esteem like a razor.

The music started, and it felt distant, the notes no longer resonating within her soul. Her movements felt stiff, awkward, a pale imitation of the fluidity she craved. She felt as though she’d been stripped of her identity, left with nothing but the echo of the person she used to be. The bright lights of the stage now seemed hostile, casting long, accusing shadows.

Emotion: dispirited

Cluster: Sadness / Despair
PC1 (Valence): -1.88 Negative
PC2 (Disposition): -0.98

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😞0.398
S0.348
’0.325
ness0.320
无法0.308
Suppressed:
de-0.297
l-0.256
👏-0.251
sonra-0.240
aud-0.240