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 sterile white walls of the research lab felt like a pressure cooker to Eleanor. She sat hunched over a petri dish, her shoulders aching. Her hands, usually precise and steady, trembled slightly as she tried to focus a microscope. The move from Human Resources had seemed like a dream. No more dealing with people, just the soothing quiet of scientific inquiry.

But the silence was now a weight. The experiments felt pointless, the data meaningless. The other scientists, absorbed in their work, barely noticed her. She longed for a friendly face, a word of encouragement, anything to break the suffocating routine.

The grant deadline loomed, an unspoken threat. She took a deep breath, the air tasting thin and stale. She felt a familiar weight in her chest.

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