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).

"You're moving to the backfield, Maya." The coach’s pronouncement, delivered with a casual shrug, felt like a punch to the gut. The familiar, rhythmic thud of the practice ball was replaced by a dull ache in Maya's hands. She'd dreamt of being a quarterback since she was a little girl, the cool precision of her passes a source of pride and purpose.

The sun beat down on the field, each ray a heavy weight pressing down on her shoulders. Her usually bright eyes, sparkling with anticipation, now held a glazed look. A knot formed in her stomach as she imagined the brutal, thankless task of blocking for others, of sacrificing her own glory. She felt like a beautiful instrument that was being tuned to play a different melody.

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