LDA showed probability problems in calculating probability of labels

data = importdata('LDA data.mat')

features=data(:,1:end-1); %split data without labels

lable=data(:,end); %get the labels

W=LDA(features,lable); %perform LDA on data

L = [ones(170884,1) features] * W';

P = exp(L) ./ repmat(sum(exp(L),1),[170884 1]);

handles.features = features;

guidata(hObject, handles);

Problem: Assuming I have seven data sets in columns to compare and a last column being label. I perform a simple LDA on it. Thing is, P gave me all the example, 0.0000079.... when its supposed to be 0.021. When all the rows add up, they equal to 1 so that probability of labels can be caluclated. Need help please!!!