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 world felt muted to Clara. Colors seemed less vibrant, sounds less distinct. Even the bright sun seemed to cast a shadow over her apartment. She wandered through the rooms, picking up objects and putting them back down. A new envelope, postmarked from her childhood town, lay on the mantelpiece. The postmark was a name she hadn't heard in ages. She almost did not open it.

The letter inside was a confession, a long-delayed accounting of a childhood cruelty. The letter's words, a cascade of regret, forced her to confront the old wound. Her fingers traced the delicate script, her pulse thudding in her ears. She felt a tightening in her chest, a pressure she didn't realize she still carried. She felt a wave of nausea wash over her.

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