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 glow of the computer screen seemed to intensify the fatigue in Amelia's eyes. She’d spent months on her app, a tool designed to connect local artists with potential buyers. Every line of code, every pixel, represented hope. Now, the venture capitalists deemed it "unoriginal."

Her shoulders slumped as she went out for a walk. The city, usually vibrant, felt oppressive. The faces of busy people seemed to blur, mocking her for wasting her time.

Rounding a corner, she saw a poster – a billboard advertising a very similar app, with identical features, even down to the logo's color palette. It was being launched next week. Her stomach churned with a sickening feeling of emptiness.

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
πŸ‘-0.251
sonra-0.240
aud-0.240